{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T00:53:27Z","timestamp":1791161607409,"version":"4.1.0"},"reference-count":223,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T00:00:00Z","timestamp":1781308800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T00:00:00Z","timestamp":1787270400000},"content-version":"vor","delay-in-days":69,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Artif Intell Rev"],"DOI":"10.1007\/s10462-026-11598-3","type":"journal-article","created":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T15:54:21Z","timestamp":1781366061000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["From individual decisions to team emergence: a survey on explainable cooperative multi-agent reinforcement learning"],"prefix":"10.1007","volume":"59","author":[{"given":"Lei","family":"Sheng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiliang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiqiang","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Honghui","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,13]]},"reference":[{"key":"11598_CR1","doi-asserted-by":"crossref","unstructured":"Acero F, Li Z (2024) Distilling reinforcement learning policies for interpretable robot locomotion: gradient boosting machines and symbolic regression. In: 2024 IEEE\/RSJ international conference on intelligent robots and systems (IROS). IEEE, pp 6840\u20136847","DOI":"10.1109\/IROS58592.2024.10802433"},{"issue":"5","key":"11598_CR2","doi-asserted-by":"publisher","first-page":"1939","DOI":"10.1109\/tai.2023.3311428","volume":"5","author":"K Acharya","year":"2023","unstructured":"Acharya K, Raza W, Dourado C, Velasquez A, Song HH (2023) Neurosymbolic reinforcement learning and planning: a survey. IEEE Trans Artif Intell 5(5):1939\u20131953. https:\/\/doi.org\/10.1109\/tai.2023.3311428","journal-title":"IEEE Trans Artif Intell"},{"key":"11598_CR3","doi-asserted-by":"crossref","unstructured":"Alahmari D (2025) Agentic control towers: multi agent llm rl. In: Accelerating logistics through generative AI, digital twins, and autonomous operations. p 161","DOI":"10.4018\/979-8-3373-7006-4.ch006"},{"key":"11598_CR4","doi-asserted-by":"crossref","unstructured":"Ameur M, Brik B, Ksentini A (2024) Leveraging llms to explain drl decisions for transparent 6g network slicing. In: 2024 IEEE 10th international conference on network softwarization (NetSoft). IEEE, pp 204\u2013212","DOI":"10.1109\/NetSoft60951.2024.10588921"},{"key":"11598_CR5","doi-asserted-by":"crossref","unstructured":"Amitai Y, Septon Y, Amir O (2024) Explaining reinforcement learning agents through counterfactual action outcomes. In: Proceedings of the AAAI conference on artificial intelligence. pp 10003\u201310011","DOI":"10.1609\/aaai.v38i9.28863"},{"key":"11598_CR6","doi-asserted-by":"publisher","unstructured":"Annasamy RM, Sycara K (2019) Towards better interpretability in deep q-networks. In: Proceedings of the AAAI conference on artificial intelligence. pp 4561\u20134569. https:\/\/doi.org\/10.1609\/aaai.v33i01.33014561","DOI":"10.1609\/aaai.v33i01.33014561"},{"issue":"25","key":"11598_CR7","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2319948121","volume":"122","author":"W Barfuss","year":"2025","unstructured":"Barfuss W, Flack J, Gokhale CS, Hammond L, Hilbe C, Hughes E, Leibo JZ, Lenaerts T, Leonard N, Levin S et al (2025) Collective cooperative intelligence. Proc Natl Acad Sci USA 122(25):e2319948121","journal-title":"Proc Natl Acad Sci USA"},{"key":"11598_CR8","doi-asserted-by":"publisher","unstructured":"Barnett SA, Wantlin K, Adams RP (2025) Measuring cooperation with counterfactual planning. In: International conference on game theory and AI for security. pp 23\u201341. https:\/\/doi.org\/10.1007\/978-3-032-08064-6_2","DOI":"10.1007\/978-3-032-08064-6_2"},{"key":"11598_CR9","doi-asserted-by":"crossref","unstructured":"Barros e S\u00e1 GC, Madeira CAG, (2025) Deep reinforcement learning in real-time strategy games: a systematic literature review. Appl Intell 55(4):243","DOI":"10.1007\/s10489-024-06220-4"},{"key":"11598_CR10","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2025.3592080\/mm1","author":"LC Bezerra","year":"2025","unstructured":"Bezerra LC, Dos Santos AM, Park S (2025) Learning policies for dynamic coalition formation in multi-robot task allocation. IEEE Robot Autom Lett. https:\/\/doi.org\/10.1109\/lra.2025.3592080\/mm1","journal-title":"IEEE Robot Autom Lett"},{"key":"11598_CR11","doi-asserted-by":"crossref","unstructured":"Boggess K, Kraus S, Feng L (2022) Toward policy explanations for multi-agent reinforcement learning. https:\/\/doi.org\/arXiv:2204.1256810.24963\/ijcai.2022\/16 arXiv preprint","DOI":"10.24963\/ijcai.2022\/16"},{"key":"11598_CR12","doi-asserted-by":"crossref","unstructured":"Boggess K, Kraus S, Feng L (2023) Explainable multi-agent reinforcement learning for temporal queries. https:\/\/doi.org\/arXiv:2305.1037810.24963\/ijcai.2023\/7 arXiv preprint","DOI":"10.24963\/ijcai.2023\/7"},{"key":"11598_CR13","unstructured":"Briglia G, Mariani S, Zambonelli F (2025) A roadmap towards improving multi-agent reinforcement learning with causal discovery and inference. arXiv preprint arXiv:2503.17803"},{"issue":"8","key":"11598_CR14","first-page":"1853","volume":"47","author":"HY Cao","year":"2024","unstructured":"Cao HY, Liu X, Dong SK et al (2024) Review of explainability research for reinforcement learning. Chin J Comput 47(8):1853\u20131882 ((in Chinese))","journal-title":"Chin J Comput"},{"issue":"19","key":"11598_CR15","doi-asserted-by":"publisher","first-page":"13163","DOI":"10.1007\/s00521-022-07960-5","volume":"37","author":"J Castellini","year":"2025","unstructured":"Castellini J, Devlin S, Oliehoek FA, Savani R (2025) Difference rewards policy gradients. Neural Comput Appl 37(19):13163\u201313186. https:\/\/doi.org\/10.1007\/s00521-022-07960-5","journal-title":"Neural Comput Appl"},{"key":"11598_CR16","unstructured":"Castro PS, Tomasev N, Anand A, Sharma N, Mohanta R, Dev A, Perlin K, Jain S, Levin K, Dabney N, Novikov W, Turner A, Eckstein GC, Daw MK, Miller ND, Stachenfeld KJ, KL (2025a) Automated discovery of interpretable cognitive programs underlying reward-guided behavior. In: Computational and systems neuroscience meeting. https:\/\/doi.org\/COSYNE2025)10.1101\/2025.02.05.636732"},{"key":"11598_CR17","doi-asserted-by":"crossref","unstructured":"Castro PS, Tomasev N, Anand A, Sharma N, Mohanta R, Dev A, Perlin K, Jain S, Levin K, Dabney N, Novikov W, Turner A, Eckstein GC, Daw MK, Miller ND, Stachenfeld KJ, KL (2025b) Discovering symbolic cognitive models from human and animal behavior. In: Proceedings of the 42nd international conference on machine learning, proceedings of machine learning research. pp 6849\u20136890 (PMLR)","DOI":"10.1101\/2025.02.05.636732"},{"key":"11598_CR18","doi-asserted-by":"crossref","unstructured":"Chai J, Fu Y, Zhao D, Zhu Y (2024) Aligning credit for multi-agent cooperation via model-based counterfactual imagination. In: Proceedings of the 23rd international conference on autonomous agents and multiagent systems. pp 281\u2013289","DOI":"10.65109\/AWZC1597"},{"key":"11598_CR27","unstructured":"Chen D, Zhang Q (2023) Context-aware Bayesian network actor-critic methods for cooperative multi-agent reinforcement learning. In: International conference on machine learning. pp 5327\u20135350 (PMLR)"},{"key":"11598_CR23","doi-asserted-by":"crossref","unstructured":"Chen X, Liu X, Zhang S, Ding B, Li K (2022) Goal consistency: an effective multi-agent cooperative method for multistage tasks. In: IJCAI, pp 172\u2013178","DOI":"10.24963\/ijcai.2022\/25"},{"issue":"4","key":"11598_CR19","doi-asserted-by":"publisher","first-page":"6627","DOI":"10.1109\/tnnls.2024.3387397","volume":"36","author":"B Chen","year":"2024","unstructured":"Chen B, Cao Z, Bai Q (2024) Satf: A scalable attentive transfer framework for efficient multiagent reinforcement learning. IEEE Trans Neural Netw Learn Syst 36(4):6627\u20136641. https:\/\/doi.org\/10.1109\/tnnls.2024.3387397","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"14","key":"11598_CR20","doi-asserted-by":"publisher","first-page":"2554","DOI":"10.3390\/buildings15142554","volume":"15","author":"S Chen","year":"2025","unstructured":"Chen S, Chen X, Bao Q, Zhang H, Wong CUI (2025a) Adaptive multi-agent reinforcement learning with graph neural networks for dynamic optimization in sports buildings. Buildings 15(14):2554. https:\/\/doi.org\/10.3390\/buildings15142554","journal-title":"Buildings"},{"key":"11598_CR24","doi-asserted-by":"publisher","unstructured":"Chen L, Li Z, Xiong Y (2025b) Boosting multi-agent collaboration with dual attention actor-critic. In: 2025 5th International conference on machine learning and intelligent systems engineering (MLISE). IEEE, pp 222\u2013229. https:\/\/doi.org\/10.1109\/mlise66443.2025.11100230","DOI":"10.1109\/mlise66443.2025.11100230"},{"key":"11598_CR25","doi-asserted-by":"crossref","unstructured":"Chen R, Milani S, Zhang Z, Sadeh N, Fang F (2025c) Making teams and influencing agents: efficiently coordinating decision trees for interpretable multi-agent reinforcement learning. https:\/\/doi.org\/arXiv:2505.1931610.1609\/aies.v8i1.36571 arXiv preprint","DOI":"10.1609\/aies.v8i1.36571"},{"key":"11598_CR26","unstructured":"Chen G, Wang G, Van Beek A, Yan MZ, Y (2025d) Emergence of hierarchies in multi-agent self-organizing systems pursuing a joint objective. arXiv:2508.09541 arXiv preprint"},{"key":"11598_CR21","doi-asserted-by":"publisher","first-page":"62457","DOI":"10.52202\/075280-2728","volume":"36","author":"Z Cheng","year":"2023","unstructured":"Cheng Z, Wu X, Yu J, Sun W, Guo W, Xing X (2023) Statemask: Explaining deep reinforcement learning through state mask. Adv Neural Inf Process Syst 36:62457\u201362487","journal-title":"Adv Neural Inf Process Syst"},{"key":"11598_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2025.110998","volume":"156","author":"J Cheng","year":"2025","unstructured":"Cheng J, Li J, Shi H, Zhang T (2025) Localizing state space for visual reinforcement learning in noisy environments. Eng Appl Artif Intell 156:110998. https:\/\/doi.org\/10.1016\/j.engappai.2025.110998","journal-title":"Eng Appl Artif Intell"},{"key":"11598_CR28","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4467882","volume":"147","author":"M Crespi","year":"2023","unstructured":"Crespi M, Ferigo A, Custode LL, Iacca G (2023) A population-based approach for multi-agent interpretable reinforcement learning. Appl Soft Comput 147:110758. https:\/\/doi.org\/10.2139\/ssrn.4467882","journal-title":"Appl Soft Comput"},{"key":"11598_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.epsr.2022.107932","volume":"209","author":"Y Dai","year":"2022","unstructured":"Dai Y, Chen Q, Zhang J, Wang X, Chen Y, Gao T, Xu P, Chen S, Liao S, Jiang H et al (2022) Enhanced oblique decision tree enabled policy extraction for deep reinforcement learning in power system emergency control. Electr Power Syst Res 209:107932. https:\/\/doi.org\/10.1016\/j.epsr.2022.107932","journal-title":"Electr Power Syst Res"},{"key":"11598_CR31","unstructured":"Daskalakis C, Golowich N, Zhang K (2023) The complexity of Markov equilibrium in stochastic games. In: The thirty sixth annual conference on learning theory, PMLR. pp 4180\u20134234"},{"key":"11598_CR30","unstructured":"Daskalakis C, Gemp I, Jiang Y, Leme RP, Papadimitriou C, Piliouras G (2024) Charting the shapes of stories with game theory. In: NeurIPS 2024 workshop on creative AI"},{"issue":"1","key":"11598_CR32","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/tcyb.2022.318066","volume":"54","author":"Y Dhebar","year":"2022","unstructured":"Dhebar Y, Deb K, Nageshrao S, Zhu L, Filev D (2022) Toward interpretable-ai policies using evolutionary nonlinear decision trees for discrete-action systems. IEEE Trans Cybern 54(1):50\u201362. https:\/\/doi.org\/10.1109\/tcyb.2022.318066","journal-title":"IEEE Trans Cybern"},{"key":"11598_CR33","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3243557","author":"S Ding","year":"2023","unstructured":"Ding S, Du W, Ding L, Zhang J, Guo L, An B (2023a) Multiagent reinforcement learning with graphical mutual information maximization. IEEE Trans Neural Netw Learn Syst. https:\/\/doi.org\/10.1109\/tnnls.2023.3243557","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"5","key":"11598_CR34","doi-asserted-by":"publisher","first-page":"3096","DOI":"10.1109\/tpami.2023.3337534","volume":"46","author":"S Ding","year":"2023","unstructured":"Ding S, Du W, Ding L, Zhang J, Guo L, An B (2023b) Robust multi-agent communication with graph information bottleneck optimization. IEEE Trans Pattern Anal Mach Intell 46(5):3096\u20133107. https:\/\/doi.org\/10.1109\/tpami.2023.3337534","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11598_CR35","doi-asserted-by":"crossref","unstructured":"Ding S, Du W, Ding L, Guo L, Zhang J (2024) Learning efficient and robust multi-agent communication via graph information bottleneck. In: Proceedings of the AAAI conference on artificial intelligence. pp 17346\u201317353","DOI":"10.1609\/aaai.v38i16.29682"},{"key":"11598_CR37","doi-asserted-by":"publisher","unstructured":"Dom\u00e8nech I Vila M, Gnatyshak D, Tormos A, Alvarez-Napagao S (2022) Testing reinforcement learning explainability methods in a multi-agent cooperative environment. In: Artificial intelligence research and development. IOS Press, pp 355\u2013364. https:\/\/doi.org\/10.3233\/faia220358","DOI":"10.3233\/faia220358"},{"key":"11598_CR36","doi-asserted-by":"crossref","unstructured":"Domenech I Vila M, Gnatyshak D, Tormos A, Gimenez-Abalos V, Alvarez-Napagao S (2024) Explaining the behaviour of reinforcement learning agents in a multi-agent cooperative environment using policy graphs. Electronics 13(3): https:\/\/doi.org\/573.10.20944\/preprints202401.1421.v1","DOI":"10.3390\/electronics13030573"},{"issue":"10","key":"11598_CR38","doi-asserted-by":"publisher","first-page":"6851","DOI":"10.1109\/tnnls.2022.3215774","volume":"34","author":"W Du","year":"2022","unstructured":"Du W, Ding S, Zhang C, Shi Z (2022) Multiagent reinforcement learning with heterogeneous graph attention network. IEEE Trans Neural Netw Learn Syst 34(10):6851\u20136860. https:\/\/doi.org\/10.1109\/tnnls.2022.3215774","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"11598_CR42","doi-asserted-by":"publisher","unstructured":"Du X, Ye Y, Zhang P, Yang Y, Chen M, Wang T (2024) Situation-dependent causal influence-based cooperative multi-agent reinforcement learning. In: Proceedings of the AAAI conference on artificial intelligence. pp 17362\u201317370. https:\/\/doi.org\/10.1609\/aaai.v38i16.29684","DOI":"10.1609\/aaai.v38i16.29684"},{"key":"11598_CR39","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3513402","author":"W Duan","year":"2024","unstructured":"Duan W, Lu J, Xuan J (2024a) Inferring latent temporal sparse coordination graph for multiagent reinforcement learning. IEEE Trans Neural Netw Learn Syst. https:\/\/doi.org\/10.1109\/tnnls.2024.3513402","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"11598_CR40","doi-asserted-by":"publisher","unstructured":"Duan W, Lu J, Xuan J (2024b) Group-aware coordination graph for multi-agent reinforcement learning. In: IJCAI international joint conference on artificial intelligence. pp 3926\u20133934. https:\/\/doi.org\/10.24963\/ijcai.2024\/434","DOI":"10.24963\/ijcai.2024\/434"},{"key":"11598_CR41","doi-asserted-by":"publisher","unstructured":"Duttagupta A, Jabbari M, Fiandrino C, Fiore M, Widmer J (2025) Symbxrl: symbolic explainable deep reinforcement learning for mobile networks. In: IEEE INFOCOM 2025-IEEE conference on computer communications. IEEE, https:\/\/doi.org\/10.1109\/infocom55648.2025.11044492","DOI":"10.1109\/infocom55648.2025.11044492"},{"key":"11598_CR43","doi-asserted-by":"publisher","unstructured":"Fan W, Yu Z, Ma C, Li C, Yang Y, Zhang X (2025) Towards efficient collaboration via graph modeling in reinforcement learning. In: Proceedings of the AAAI conference on artificial intelligence. pp 16505\u201316513. https:\/\/doi.org\/10.1609\/aaai.v39i16.33813","DOI":"10.1609\/aaai.v39i16.33813"},{"key":"11598_CR44","doi-asserted-by":"publisher","DOI":"10.1109\/tetci.2024.3449873","author":"Q Fu","year":"2024","unstructured":"Fu Q, Qiu T, Yi J, Pu Z, Ai X (2024) Self-clustering hierarchical multi-agent reinforcement learning with extensible cooperation graph. IEEE Trans Emerg Topics Comput Intell. https:\/\/doi.org\/10.1109\/tetci.2024.3449873","journal-title":"IEEE Trans Emerg Topics Comput Intell"},{"key":"11598_CR45","doi-asserted-by":"publisher","DOI":"10.1109\/tcds.2025.3578001","author":"Y Fu","year":"2025","unstructured":"Fu Y, Zhu Y, Li H, Zhao Z, Chai J, Zhao D (2025) Cpig: Leveraging consistency policy with intention guidance for multi-agent exploration. IEEE Trans Cogn Dev Syst. https:\/\/doi.org\/10.1109\/tcds.2025.3578001","journal-title":"IEEE Trans Cogn Dev Syst"},{"issue":"9","key":"11598_CR46","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3648472","volume":"56","author":"J Gajcin","year":"2024","unstructured":"Gajcin J, Dusparic I (2024) Redefining counterfactual explanations for reinforcement learning: overview, challenges and opportunities. ACM Comput Surv 56(9):1\u201333","journal-title":"ACM Comput Surv"},{"key":"11598_CR47","doi-asserted-by":"publisher","DOI":"10.1109\/tsmc.2025.3604230","author":"Z Gao","year":"2025","unstructured":"Gao Z, Qu C, Hao Y, Ke L (2025) Communication in multiagent reinforcement learning via counterfactual message value. IEEE Trans Syst Man Cybern Syst. https:\/\/doi.org\/10.1109\/tsmc.2025.3604230","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"issue":"9","key":"11598_CR48","doi-asserted-by":"publisher","first-page":"9701","DOI":"10.1007\/s10489-021-02873-7","volume":"52","author":"H Ge","year":"2022","unstructured":"Ge H, Ge Z, Sun L, Wang Y (2022) Enhancing cooperation by cognition differences and consistent representation in multi-agent reinforcement learning. Appl Intell 52(9):9701\u20139716. https:\/\/doi.org\/10.1007\/s10489-021-02873-7","journal-title":"Appl Intell"},{"key":"11598_CR49","doi-asserted-by":"publisher","unstructured":"Gemp I, Mckee KR, Everett R, Guzm\u00e1n D, Bachrach E, Balduzzi Y, Tacchetti D, A (2022) D3c: Reducing the price of anarchy in multi-agent learning. In: Proceedings of the 21st international conference on autonomous agents and multiagent systems. international foundation for autonomous agents and multiagent systems. Richland, SC, AAMAS, pp 498\u2013506. https:\/\/doi.org\/10.5555\/3535850.3535907","DOI":"10.5555\/3535850.3535907"},{"key":"11598_CR50","unstructured":"Gemp I, Patel R, Bachrach Y, Lanctot M, Dasagi V, Marris L, Piliouras G, Liu S, Tuyls K (2024) Steering language models with game-theoretic solvers. arXiv preprint arXiv:2402.01704"},{"key":"11598_CR51","doi-asserted-by":"crossref","unstructured":"Ge Z, Zhu Y, Chen C (2025) Concept learning for cooperative multi-agent reinforcement learning. In: 2025 IEEE 26th China conference on system simulation technology and its applications (CCSSTA). IEEE, pp 625\u2013631","DOI":"10.1109\/IEEECONF65522.2025.11136965"},{"key":"11598_CR52","doi-asserted-by":"crossref","unstructured":"Gimenez-Abalos V, Alvarez-Napagao S, Tormos A, Cort\u00e9s U, V\u00e1zquez-Salceda J (2025) Policy graphs and intention: answering \u201cwhy\u201d and \u201chow\u201d from a telic perspective. In: Proceedings of the 24th international conference on autonomous agents and multiagent systems. International Foundation for Autonomous Agents and Multiagent Systems. Richland, SC, AAMAS, pp 904\u2013913","DOI":"10.65109\/DRDE3929"},{"key":"11598_CR53","unstructured":"Godfrey T, Hunt W, Soorati MD (2024) Marlin: Multi-agent reinforcement learning guided by language-based inter-robot negotiation. https:\/\/doi.org\/arXiv:2410.1438310.17760\/d20467227 arXiv preprint"},{"issue":"3","key":"11598_CR54","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1109\/TSE.2013.59","volume":"40","author":"A Groce","year":"2014","unstructured":"Groce A, Kulesza T, Zhang C, Shamasunder S, Burnett M, Wong WK, Stumpf S, Das S, Shinsel A, Bice F, McIntosh K (2014) You are the only possible oracle: effective test selection for end users of interactive machine learning systems. IEEE Trans Softw Eng 40(3):307\u2013323. https:\/\/doi.org\/10.1109\/TSE.2013.59","journal-title":"IEEE Trans Softw Eng"},{"key":"11598_CR55","unstructured":"Grupen N, Jaques N, Kim B, Omidshafiei S (2022) Concept-based understanding of emergent multi-agent behavior. In: Deep reinforcement learning workshop NeurIPS"},{"key":"11598_CR56","doi-asserted-by":"publisher","first-page":"1020","DOI":"10.1109\/tnnls.2024.3420791","volume":"35","author":"C Guan","year":"2022","unstructured":"Guan C, Chen F, Yuan L, Wang C, Yin H, Zhang Z, Yu Y (2022) Efficient multi-agent communication via self-supervised information aggregation. Adv Neural Inf Process Syst 35:1020\u20131033. https:\/\/doi.org\/10.1109\/tnnls.2024.3420791","journal-title":"Adv Neural Inf Process Syst"},{"key":"11598_CR57","doi-asserted-by":"publisher","unstructured":"Guo YS, Campbell J, Stepputtis S, Li R (2023) Explainable action advising for multi-agent reinforcement learning. In: Proceedings of the 2023 IEEE international conference on robotics and automation (ICRA). pp 5515\u20135521. https:\/\/doi.org\/10.1109\/ICRA48891.2023.10160557","DOI":"10.1109\/ICRA48891.2023.10160557"},{"key":"11598_CR58","doi-asserted-by":"publisher","DOI":"10.25236\/ijfet.2024.060510","author":"H Guo","year":"2024","unstructured":"Guo H, Wang X, Ma N, Zhang Y (2024) Robust reinforcement learning for robotic manipulation using lite vit and saliency maps. Int J Front Eng Technol. https:\/\/doi.org\/10.25236\/ijfet.2024.060510","journal-title":"Int J Front Eng Technol"},{"key":"11598_CR59","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1109\/lcsys.2024.3349511","volume":"8","author":"Y Gurses","year":"2024","unstructured":"Gurses Y, Buyukdemirci K, Yildiz Y (2024) Developing driving strategies efficiently: a skill-based hierarchical reinforcement learning approach. IEEE Control Syst Lett 8:121\u2013126. https:\/\/doi.org\/10.1109\/lcsys.2024.3349511","journal-title":"IEEE Control Syst Lett"},{"key":"11598_CR60","unstructured":"Gyevn\u00e1r B, Lucas CG, Albrecht SV, Cohen SB (2025) Integrating counterfactual simulations with language models for explaining multi-agent behaviour. https:\/\/doi.org\/arXiv:2505.1780110.1109\/wsc63780.2024.10838923 arXiv preprint"},{"key":"11598_CR61","doi-asserted-by":"crossref","unstructured":"Han D, Lu CX, Michalak T, Wooldridge M (2022a) Multiagent model-based credit assignment for continuous control. In: Proceedings of the 21st international conference on autonomous agents and multiagent systems. pp 571\u2013579","DOI":"10.65109\/OUOV7693"},{"key":"11598_CR62","doi-asserted-by":"publisher","unstructured":"Han Y, Piao H, Hou Y, Sun Y, Sun Z, Zhou D, Yang S, Peng X, Fan S (2022b) Deep relationship graph reinforcement learning for multi-aircraft air combat. In: 2022 International joint conference on neural networks (IJCNN). IEEE, https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9892208","DOI":"10.1109\/ijcnn55064.2022.9892208"},{"key":"11598_CR63","doi-asserted-by":"publisher","unstructured":"Hao Q, Huang W, Feng T, Yuan J, Li Y (2023) Gat-mf: Graph attention mean field for very large scale multi-agent reinforcement learning. In: Proceedings of the 29th ACM SIGKDD conference on knowledge discovery and data mining. pp 685\u2013697. https:\/\/doi.org\/10.1145\/3580305.3599359","DOI":"10.1145\/3580305.3599359"},{"issue":"5","key":"11598_CR64","doi-asserted-by":"publisher","first-page":"3925","DOI":"10.1007\/s00521-024-10655-8","volume":"37","author":"X He","year":"2025","unstructured":"He X, Ge H, Hao Z, Hou Y (2025) Maric:an efficient multi-agent real-time intention-based communication model for team cooperation. Neural Comput Appl 37(5):3925\u20133942. https:\/\/doi.org\/10.1007\/s00521-024-10655-8","journal-title":"Neural Comput Appl"},{"key":"11598_CR65","doi-asserted-by":"publisher","unstructured":"Helmboldt R (2025) Evaluating saliency map methods in reinforcement learning. Hochschule f\u00fcr Angewandte Wissenschaften Hamburg, https:\/\/doi.org\/10.1088\/1742-6596\/1757\/1\/012075 (PhD thesis)","DOI":"10.1088\/1742-6596\/1757\/1\/012075"},{"issue":"1","key":"11598_CR66","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1109\/mci.2021.3129959","volume":"17","author":"A Heuillet","year":"2022","unstructured":"Heuillet A, Couthouis F, D\u00edaz-Rodr\u00edguez N (2022) Collective explainable ai: explaining cooperative strategies and agent contribution in multiagent reinforcement learning with shapley values. IEEE Comput Intell Mag 17(1):59\u201371. https:\/\/doi.org\/10.1109\/mci.2021.3129959","journal-title":"IEEE Comput Intell Mag"},{"key":"11598_CR67","unstructured":"He P, Wang W, Sun C, Wang Y (2025) Hierarchical cognitive graph autoencoder for multi-agent reinforcement learning. In: Proceedings of the annual meeting of the cognitive science society"},{"key":"11598_CR68","doi-asserted-by":"publisher","DOI":"10.1109\/spec62217.2024.10893249","volume":"155","author":"D Hu","year":"2024","unstructured":"Hu D, Li Z, Ye Z, Peng Y, Xi W, Cai T (2024a) Multi-agent graph reinforcement learning for decentralized volt-var control in power distribution systems. Int J Electr Power Energy Syst 155:109531. https:\/\/doi.org\/10.1109\/spec62217.2024.10893249","journal-title":"Int J Electr Power Energy Syst"},{"key":"11598_CR71","doi-asserted-by":"crossref","unstructured":"Hu T, Pu Z, Qiu AX, Yi T, J (2024b) Measuring policy distance for multi-agent reinforcement learning. In: Proceedings of the international joint conference on autonomous agents and multiagent systems. pp 834\u2013844","DOI":"10.65109\/KZPX1537"},{"key":"11598_CR72","unstructured":"Hu S, Shen L, Zhang Y, Tao D (2024c) Learning multi-agent communication from graph modeling perspective. In: 12th International conference on learning representations, ICLR 2024"},{"key":"11598_CR73","unstructured":"Hu Z, Zhang Z, Li H, Chen C, Ding H, Wang Z (2024d) Attention-guided contrastive role representations for multi-agent reinforcement learning. In: 12th International conference on learning representations (ICLR)"},{"key":"11598_CR69","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2025.3560227","author":"S Huang","year":"2025","unstructured":"Huang S, Sun C, Wang RQ, Pompili D (2025) Toward adaptive and coordinated transportation systems: a multi-personality multi-agent meta-reinforcement learning framework. IEEE Trans Intell Transp Syst. https:\/\/doi.org\/10.1109\/tits.2025.3560227","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"11598_CR70","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2022.903875","volume":"5","author":"T Huber","year":"2022","unstructured":"Huber T, Limmer B, Andr\u00e9 E (2022) Benchmarking perturbation-based saliency maps for explaining atari agents. Front Artif Intell 5:903875. https:\/\/doi.org\/10.3389\/frai.2022.903875","journal-title":"Front Artif Intell"},{"key":"11598_CR74","unstructured":"Ibrahim M, Fayad A (2022) Hierarchical strategies for cooperative multi-agent reinforcement learning. https:\/\/doi.org\/arXiv:2212.0739710.2139\/ssrn.4888294 arXiv preprint"},{"key":"11598_CR75","doi-asserted-by":"publisher","unstructured":"Itaya H, Sagawa T, Hirakawa T, Yamashita T, Fujiyoshi H (2023) Visual explanation for cooperative behavior in multi-agent reinforcement learning. In: 2023 International joint conference on neural networks (IJCNN). IEEE, https:\/\/doi.org\/10.1109\/iros58592.2024.10801292","DOI":"10.1109\/iros58592.2024.10801292"},{"key":"11598_CR76","unstructured":"Iturria-Rivera PE, Gaigalas R, Elsayed M, Bavand M, Ozcan Y, Erol-Kantarci M (2024) Explainable multi-agent reinforcement learning for extended reality codec adaptation. arXiv preprint https:\/\/doi.org\/arXiv:2411.14264"},{"issue":"7","key":"11598_CR77","doi-asserted-by":"publisher","first-page":"1591","DOI":"10.1109\/jas.2024.124281","volume":"11","author":"K Jiang","year":"2024","unstructured":"Jiang K, Liu W, Wang Y, Dong L, Sun C (2024) Discovering latent variables for the tasks with confounders in multi-agent reinforcement learning. IEEE\/CAA J Automatica Sinica 11(7):1591\u20131604. https:\/\/doi.org\/10.1109\/jas.2024.124281","journal-title":"IEEE\/CAA J Automatica Sinica"},{"key":"11598_CR78","unstructured":"Jiang Z, Zhang B, Wei A, Xu Z (2025) Qllm: Do we really need a mixing network for credit assignment in multi-agent reinforcement learning? arXiv preprint arXiv:2504.12961"},{"key":"11598_CR79","doi-asserted-by":"publisher","unstructured":"Ji B, Li G, Xiao G (2023) Enhancing the interpretability of deep multi-agent reinforcement learning via neural logic reasoning. In: International conference on artificial neural networks. Springer, pp 199\u2013210. https:\/\/doi.org\/10.1007\/978-3-031-44204-9_17","DOI":"10.1007\/978-3-031-44204-9_17"},{"key":"11598_CR83","unstructured":"Ji M, Xu G, Wang L (2025) Cora: Coalitional rational advantage decomposition for multi-agent policy gradients. https:\/\/doi.org\/arXiv:2506.0426510.48550\/arXiv.2506.04265 arXiv preprint"},{"key":"11598_CR80","doi-asserted-by":"publisher","unstructured":"Jin J, Sun G, Chen S, Li Y, Liao Y, Mao W, Shen L (2025a) A multi-agent robust deep reinforcement learning approach for coordination of power distribution networks and microgrids with limited information exchange. J Modern Power Syst Clean Energy 1\u201312. https:\/\/doi.org\/10.1109\/TPWRS.2023.3276827","DOI":"10.1109\/TPWRS.2023.3276827"},{"key":"11598_CR81","doi-asserted-by":"crossref","unstructured":"Jin W, Du H, Liu G, Kim DI (2025b) Curriculum learning with counterfactual group relative policy advantage for multi-agent reinforcement learning. https:\/\/doi.org\/arXiv:2506.07548 arXiv preprint Preprint at https:\/\/doi.org\/arxiv.org\/abs\/2506.07548","DOI":"10.2139\/ssrn.6477659"},{"key":"11598_CR82","doi-asserted-by":"crossref","unstructured":"Jin W, Du H, Zhao B, Tian X, Shi B, Yang G (2025c) A comprehensive survey on multi-agent cooperative decision-making: scenarios, approaches, challenges and perspectives. https:\/\/doi.org\/arxiv.org\/abs\/2503.13415 arXiv Preprint at","DOI":"10.2139\/ssrn.5106265"},{"key":"11598_CR84","doi-asserted-by":"crossref","unstructured":"Kailas S, Jain S, Ravichandar H (2025) Evaluating and improving graph-based explanation methods for multi-agent coordination. https:\/\/doi.org\/arXiv:2502.0988910.1109\/tg.2023.3263013 arXiv preprint","DOI":"10.65109\/SLGY9550"},{"key":"11598_CR85","doi-asserted-by":"crossref","unstructured":"Kazhdan D, Shams Z, Lio P (2020) MARLeME: A multi-agent reinforcement learning model extraction library. In: 2020 International joint conference on neural networks (IJCNN). glasgow, UK, pp 1\u20138","DOI":"10.1109\/IJCNN48605.2020.9207564"},{"key":"11598_CR86","doi-asserted-by":"publisher","unstructured":"Kim WK, Lee Y, Woo H (2022) Mean-variance based risk-sensitive reinforcement learning with interpretable attention. In: Proceedings of the 2022 5th international conference on machine vision and applications. pp 104\u2013109. https:\/\/doi.org\/10.1145\/3523111.3523127","DOI":"10.1145\/3523111.3523127"},{"key":"11598_CR87","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2024.3472213","author":"GS Kim","year":"2024","unstructured":"Kim GS, Lee S, Woo T, Park S (2024a) Cooperative reinforcement learning for military drones over large-scale battlefields. IEEE Trans Intell. https:\/\/doi.org\/10.1109\/tiv.2024.3472213","journal-title":"IEEE Trans Intell"},{"issue":"4","key":"11598_CR88","doi-asserted-by":"publisher","first-page":"3797","DOI":"10.1109\/tnsm.2024.3392393","volume":"21","author":"J Kim","year":"2024","unstructured":"Kim J, Park S, Jung S, Cordeiro C (2024b) Cooperative multi-uav positioning for aerial internet service management: a multi-agent deep reinforcement learning approach. IEEE Trans Netw Serv Manage 21(4):3797\u20133812. https:\/\/doi.org\/10.1109\/tnsm.2024.3392393","journal-title":"IEEE Trans Netw Serv Manage"},{"key":"11598_CR89","unstructured":"Kortvelesy R, Prorok A (2022) Qgnn: Value function factorisation with graph neural networks. arXiv preprint arXiv:2205.13005"},{"issue":"19","key":"11598_CR90","doi-asserted-by":"publisher","first-page":"5812","DOI":"10.1080\/00207543.2021.1972179","volume":"60","author":"A Kuhnle","year":"2022","unstructured":"Kuhnle A, May MC, Sch\u00e4fer L, Lanza G (2022) Explainable reinforcement learning in production control of job shop manufacturing system. Int J Prod Res 60(19):5812\u20135834. https:\/\/doi.org\/10.1080\/00207543.2021.1972179","journal-title":"Int J Prod Res"},{"issue":"3","key":"11598_CR91","doi-asserted-by":"publisher","first-page":"615","DOI":"10.1109\/TCDS.2024.3504256","volume":"17","author":"Y Lan","year":"2025","unstructured":"Lan Y, Gao H, Xu X, Fang Q, Zeng Y (2025) Smart: Sequential multiagent reinforcement learning with role assignment using transformer. IEEE Trans Cogn Dev Syst 17(3):615\u2013630. https:\/\/doi.org\/10.1109\/TCDS.2024.3504256","journal-title":"IEEE Trans Cogn Dev Syst"},{"key":"11598_CR92","doi-asserted-by":"crossref","unstructured":"Lei L, Wu C, Chen H (2025) Dynamic decoupling-driven cooperative pursuit for multi-uav systems: a multi-agent reinforcement learning policy optimization approach. Comput Mater","DOI":"10.32604\/cmc.2025.067117"},{"issue":"11","key":"11598_CR93","doi-asserted-by":"publisher","first-page":"8618","DOI":"10.1109\/tpami.2021.3102140","volume":"44","author":"W Li","year":"2022","unstructured":"Li W, Wang X, Jin B, Luo D, Zha H (2022) Structured cooperative reinforcement learning with time-varying composite action space. IEEE Trans Pattern Anal Mach Intell 44(11):8618\u20138634. https:\/\/doi.org\/10.1109\/tpami.2021.3102140","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"2","key":"11598_CR94","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1109\/tg.2023.3263013","volume":"16","author":"W Li","year":"2023","unstructured":"Li W, Liu W, Shao S, Huang S, Song A (2023) Attention-based intrinsic reward mixing network for credit assignment in multiagent reinforcement learning. IEEE Trans Games 16(2):270\u2013281. https:\/\/doi.org\/10.1109\/tg.2023.3263013","journal-title":"IEEE Trans Games"},{"key":"11598_CR95","doi-asserted-by":"publisher","unstructured":"Li H, Mahjoub N, Chalaki H, Tadiparthi B, Lee V, K, Pari M, Lewis E, Sycara C, K (2024a) Language grounded multi-agent reinforcement learning with human-interpretable communication. Adv Neural Inf Process Syst 37:87908\u201387933. https:\/\/doi.org\/10.5555\/3737916.3740706","DOI":"10.5555\/3737916.3740706"},{"key":"11598_CR101","doi-asserted-by":"crossref","unstructured":"Li L, Donato E, Lomonaco V, Falotico E (2024b) Continual policy distillation of reinforcement learning-based controllers for soft robotic in-hand manipulation. In: 2024 IEEE 7th international conference on soft robotics (RoboSoft). IEEE, pp 1026\u20131033","DOI":"10.1109\/RoboSoft60065.2024.10522027"},{"key":"11598_CR102","unstructured":"Li D, Dong H, Wang L, Qiao B, Qin S, Lin Q, Zhang D, Zhang Q, Xu Z, Zhang B (2024c) Verco: Learning coordinated verbal communication for multi-agent reinforcement learning. arXiv:2404.17780 arXiv preprint"},{"key":"11598_CR103","unstructured":"Li X, Liu Z, Chen S, Zhang J (2024d) Individual contributions as intrinsic exploration scaffolds for multi-agent reinforcement learning. In: Proceedings of machine learning research, pp 28387\u201328402, https:\/\/www.scopus.com\/inward\/record.uri?eid=2-s2.0-85203844543&partnerID=40&md5=4935fd0bdb41650fdbafc39e18b1d287"},{"key":"11598_CR104","doi-asserted-by":"publisher","unstructured":"Li J, Liu Z, Su Z, Zhou Z (2024e) Rbhar: Role-based heterogeneous action representation in multi-agent reinforcement learning. In: International conference on neural information processing. Springer, pp 182\u2013196. https:\/\/doi.org\/10.1007\/978-981-96-6579-2_13","DOI":"10.1007\/978-981-96-6579-2_13"},{"key":"11598_CR116","doi-asserted-by":"publisher","unstructured":"Li C, Zhang Y, Wang J, Hu Y, Dong S, Li W, Lv T, Fan C, Gao Y (2024f) Optimistic value instructors for cooperative multi-agent reinforcement learning. In: Proceedings of the AAAI conference on artificial intelligence. pp 17453\u201317460. https:\/\/doi.org\/10.1609\/aaai.v38i16.29694","DOI":"10.1609\/aaai.v38i16.29694"},{"key":"11598_CR96","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.70029","author":"X Li","year":"2025","unstructured":"Li X, Li Z, Yang X, Yu X, Qiu J (2025a) Multi-agent target defense differential game: a hierarchical recognition-allocation-execution learning approach. Int J Robust Nonlinear Control. https:\/\/doi.org\/10.1002\/rnc.70029","journal-title":"Int J Robust Nonlinear Control"},{"issue":"7","key":"11598_CR97","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1007\/s10489-025-06473-7","volume":"55","author":"P Li","year":"2025","unstructured":"Li P, Fei Q, Chen Z (2025b) Interpretable multi-agent reinforcement learning via multi-head variational autoencoders. Appl Intell 55(7):577. https:\/\/doi.org\/10.1007\/s10489-025-06473-7","journal-title":"Appl Intell"},{"key":"11598_CR100","unstructured":"Li Y, Cao Z, Qiao J, Hu S (2025c) Nucleolus credit assignment for effective coalitions in multi-agent reinforcement learning. In: Proceedings of the international joint conference on autonomous agents and multiagent systems, AAMAS, pp 1318\u20131326, https:\/\/www.scopus.com\/inward\/record.uri?eid=2-s2.0-105009820202&partnerID=40&md5=9f5719eb89f638ab1b900e254d8470b0"},{"key":"11598_CR115","doi-asserted-by":"publisher","unstructured":"Li M, Wang Q, Xu Y (2025d) Gtde: Grouped training with decentralized execution for multi-agent actor-critic. In: Proceedings of the AAAI conference on artificial intelligence. pp 18368\u201318376. https:\/\/doi.org\/10.1609\/aaai.v39i17.34021","DOI":"10.1609\/aaai.v39i17.34021"},{"key":"11598_CR98","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2025.109461","volume":"205","author":"Z Li","year":"2026","unstructured":"Li Z, Agyeman BT, Mitrai I, Daoutidis P (2026) Learning to control inexact benders decomposition via reinforcement learning. Comput Chem Eng 205:109461. https:\/\/doi.org\/10.1016\/j.compchemeng.2025.109461 (https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0098135425004648)","journal-title":"Comput Chem Eng"},{"key":"11598_CR99","unstructured":"Liang Y, Wu H, Wang H, Cai H (2024) Asynchronous credit assignment for multi-agent reinforcement learning. https:\/\/doi.org\/arXiv:2408.0369210.24963\/ijcai.2024\/20 arXiv preprint"},{"key":"11598_CR105","unstructured":"Lin M, Shi S, Guo Y, Tadiparthi V, Chalaki B, Pari EM, Stepputtis S, Kim W, Campbell J, Sycara K (2025) Speaking the language of teamwork: Llm-guided credit assignment in multi-agent reinforcement learning. arXiv preprint https:\/\/doi.org\/arXiv:2502.03723"},{"key":"11598_CR111","doi-asserted-by":"crossref","unstructured":"Liu Y, Dou Y, Li Y, Xu X, Liu D (2022a) Temporal dynamic weighted graph convolution for multi-agent reinforcement learning. In: Proceedings of the annual meeting of the cognitive science society, openreview.net\/forum?id=X6FjJM3EYC","DOI":"10.1109\/ICME52920.2022.9859945"},{"key":"11598_CR112","doi-asserted-by":"publisher","unstructured":"Liu Y, Li Y, Xu X, Liu D, Dou Y (2022b) Rogc: Role-oriented graph convolution based multi-agent reinforcement learning. In: 2022 IEEE international conference on multimedia and expo (ICME). IEEE, https:\/\/doi.org\/10.1109\/icme52920.2022.9859945","DOI":"10.1109\/icme52920.2022.9859945"},{"issue":"5","key":"11598_CR106","first-page":"2300","volume":"34","author":"X Liu","year":"2023","unstructured":"Liu X, Liu SY, Zhuang YK, Gao Y (2023a) Explainable reinforcement learning: basic problems exploration and method survey. J Softw 34(5):2300\u20132316 ((in Chinese))","journal-title":"J Softw"},{"key":"11598_CR113","doi-asserted-by":"publisher","unstructured":"Liu Z, Wan L, Sui X, Chen Z, Sun K, Lan X (2023b) Deep hierarchical communication graph in multi-agent reinforcement learning. IJCAI 208\u2013216. https:\/\/doi.org\/10.24963\/ijcai.2023\/24","DOI":"10.24963\/ijcai.2023\/24"},{"key":"11598_CR114","unstructured":"Liu Z, Zhu Y, Chen C (2023c) Na2q: Neural attention additive model for interpretable multi-agent q-learning. arXiv pp. pp 22539\u201322558"},{"issue":"12","key":"11598_CR107","doi-asserted-by":"publisher","first-page":"8157","DOI":"10.1109\/tpami.2024.3399936\/mm1","volume":"46","author":"S Liu","year":"2024","unstructured":"Liu S, Song J, Zhou Y, Yu N, Chen K, Feng Z, Song M (2024a) Interaction pattern disentangling for multi-agent reinforcement learning. IEEE Trans Pattern Anal Mach Intell 46(12):8157\u20138172. https:\/\/doi.org\/10.1109\/tpami.2024.3399936\/mm1","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11598_CR110","unstructured":"Liu C, Cong J, Chen B, Jin Y, Zhu E (2024b) Guiding multi-agent multi-task reinforcement learning by a hierarchical framework with logical reward shaping. arXiv preprint https:\/\/doi.org\/arXiv:2411.01184"},{"key":"11598_CR108","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2025.113377","volume":"316","author":"D Liu","year":"2025","unstructured":"Liu D, Ren F, Yan J, Su G, Kato S, Gu W, Zhang M (2025a) Human attention guided multiagent hierarchical reinforcement learning for heterogeneous agents. Knowl-Based Syst 316:113377. https:\/\/doi.org\/10.1016\/j.knosys.2025.113377","journal-title":"Knowl-Based Syst"},{"key":"11598_CR109","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3540467","author":"Z Liu","year":"2025","unstructured":"Liu Z, Zhu Y, Wang Z, Gao Y, Chen C (2025b) Mixrts: Toward interpretable multi-agent reinforcement learning via mixing recurrent soft decision trees. IEEE Trans Pattern Anal Mach Intell. https:\/\/doi.org\/10.1109\/tpami.2025.3540467","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11598_CR117","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2025.3543810","author":"S Lu","year":"2025","unstructured":"Lu S, Cai Y, Liu Z, Lian Y, Chen L, Wang H (2025) A preference-based multi-agent federated reinforcement learning algorithm framework for trustworthy interactive urban autonomous driving. IEEE Trans Intell Transp Syst. https:\/\/doi.org\/10.1109\/tits.2025.3543810","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"11598_CR118","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.127256","volume":"277","author":"A Luvisutto","year":"2025","unstructured":"Luvisutto A, Celani A, Renda F, Stefanini C, De Masi G (2025) Enhancing collaboration in uncertain environment: multi-agent reinforcement learning for underwater monitoring. Expert Syst Appl 277:127256. https:\/\/doi.org\/10.1016\/j.eswa.2025.127256","journal-title":"Expert Syst Appl"},{"issue":"1","key":"11598_CR119","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1109\/TETCI.2023.3309738","volume":"8","author":"T Ma","year":"2023","unstructured":"Ma T, Peng K, Rong H, Qian Y (2023) Hierarchical coordination multi-agent reinforcement learning with Spatio-temporal abstraction. IEEE Trans Emerg Topics Comput Intell 8(1):533\u2013547","journal-title":"IEEE Trans Emerg Topics Comput Intell"},{"key":"11598_CR120","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2025.111486","volume":"158","author":"J Ma","year":"2025","unstructured":"Ma J, Li C, Feng Z, Xiao L (2025a) Dynamic visual attention-based neuron awakening and shifting in deep reinforcement learning. Eng Appl Artif Intell 158:111486. https:\/\/doi.org\/10.1016\/j.engappai.2025.111486","journal-title":"Eng Appl Artif Intell"},{"key":"11598_CR121","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4890272","author":"Q Ma","year":"2025","unstructured":"Ma Q, Liu Z, Liu X (2025b) Theoretically interpretable multi-agent reinforcement learning for continuous double auction-based p2p energy trading. CSEE J Power Energy Syst. https:\/\/doi.org\/10.2139\/ssrn.4890272","journal-title":"CSEE J Power Energy Syst"},{"key":"11598_CR122","unstructured":"Mahjoub O, De Kock R, Singh S, Khlifi W, Vall A, Ka T, Pretorius A (2023) Efficiently quantifying individual agent importance in cooperative marl https:\/\/doi.org\/arXiv:2312.08466 arXiv preprint"},{"key":"11598_CR123","doi-asserted-by":"crossref","unstructured":"Mahmud S, Saisubramanian S, Zilberstein S (2023) Explanation-guided reward alignment. IJCAI. pp 473\u2013482","DOI":"10.24963\/ijcai.2023\/53"},{"key":"11598_CR124","unstructured":"Maliha M, Hougen D (2025) Magic-mask: Multi-agent guided inter-agent collaboration with mask-based explainability for reinforcement learning. https:\/\/doi.org\/arXiv:2510.0027410.48550\/arXiv.2510.00274 arXiv preprint"},{"key":"11598_CR125","doi-asserted-by":"crossref","unstructured":"Mehmeti A, Gigante G, Venticinque S (2025) Explainable reinforcement learning for assisting air traffic controllers. In: International conference on advanced information networking and applications. Springer, pp 148\u2013157","DOI":"10.1007\/978-3-031-87778-0_14"},{"key":"11598_CR126","unstructured":"Meli D, Morasso C, Castellini A, Farinelli A (2025) What are you saying? explaining communication in multi-agent reinforcement learning. In: 11th Italian workshop on artificial intelligence and robotics, vol 2024. (short6.pdf)"},{"key":"11598_CR127","doi-asserted-by":"publisher","unstructured":"Meng X, Tan Y (2024) Pmac: Personalized multi-agent communication. In: Proceedings of the AAAI conference on artificial intelligence. pp 17505\u201317513. https:\/\/doi.org\/10.1609\/aaai.v38i16.29700","DOI":"10.1609\/aaai.v38i16.29700"},{"key":"11598_CR128","unstructured":"Milani S, Topin N, Veloso M, Fang F (2022a) A survey of explainable reinforcement learning https:\/\/doi.org\/arxiv.org\/abs\/2202.08434 Preprint at"},{"key":"11598_CR129","doi-asserted-by":"publisher","unstructured":"Milani S, Zhang Z, Topin N, Shi ZR, Kamhoua C, Papalexakis EE, Fang F (2022b) Maviper: Learning decision tree policies for interpretable multi-agent reinforcement learning. In: Joint European conference on machine learning and knowledge discovery in databases. Springer, pp 251\u2013266. https:\/\/doi.org\/10.1007\/978-3-031-26412-2_16","DOI":"10.1007\/978-3-031-26412-2_16"},{"key":"11598_CR130","doi-asserted-by":"publisher","unstructured":"Miyake K, Ito H, Faloutsos C, Matsumoto H, Morishima A (2024) Netevolve: Social network forecasting using multi-agent reinforcement learning with interpretable features. In: Proceedings of the ACM web conference. pp 2542\u20132551. https:\/\/doi.org\/10.1145\/3589334.3647982","DOI":"10.1145\/3589334.3647982"},{"issue":"7540","key":"11598_CR131","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G, Petersen S, Beattie C, Sadik A, Antonoglou I, King H, Kumaran D, Wierstra D, Legg S, Hassabis D (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529\u2013533","journal-title":"Nature"},{"issue":"14","key":"11598_CR132","doi-asserted-by":"publisher","first-page":"8454","DOI":"10.3390\/app13148454","volume":"13","author":"Y Motokawa","year":"2023","unstructured":"Motokawa Y, Sugawara T (2023a) eda3-x: Distributed attentional actor architecture for interpretability of coordinated behaviors in multi-agent systems. Appl Sci 13(14):8454. https:\/\/doi.org\/10.3390\/app13148454","journal-title":"Appl Sci"},{"key":"11598_CR133","doi-asserted-by":"publisher","first-page":"2798","DOI":"10.1016\/j.procs.2023.10.272","volume":"225","author":"Y Motokawa","year":"2023","unstructured":"Motokawa Y, Sugawara T (2023b) Strategy-following multi-agent deep reinforcement learning through external high-level instruction. Procedia Comput Sci 225:2798\u20132807. https:\/\/doi.org\/10.1016\/j.procs.2023.10.272","journal-title":"Procedia Comput Sci"},{"key":"11598_CR134","doi-asserted-by":"publisher","unstructured":"Motokawa Y, Sugawara T (2023c) Interpretability for conditional coordinated behavior in multi-agent reinforcement learning. In: 2023 International joint conference on neural networks (IJCNN). IEEE, https:\/\/doi.org\/10.1109\/ijcnn54540.2023.10191825","DOI":"10.1109\/ijcnn54540.2023.10191825"},{"key":"11598_CR135","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4888294","volume":"186","author":"X Mu","year":"2025","unstructured":"Mu X, Zhuo HH, Chen C, Zhang K, Yu C, Hao J (2025) Hierarchical task network-enhanced multi-agent reinforcement learning: toward efficient cooperative strategies. Neural Netw 186:107254. https:\/\/doi.org\/10.2139\/ssrn.4888294","journal-title":"Neural Netw"},{"key":"11598_CR136","doi-asserted-by":"crossref","unstructured":"Nagpal K, Dong D, Bouvier JB, Mehr N (2025) Leveraging large language models for effective and explainable multi-agent credit assignment. In: Proceedings of the international joint conference on autonomous agents and multiagent systems. pp 1501\u20131510","DOI":"10.65109\/NOKW1037"},{"key":"11598_CR137","unstructured":"Na H, Lee K, Lee S, Moon IC (2025) Trajectory-class-aware multi-agent reinforcement learning. In: The thirteenth international conference on learning representations"},{"issue":"2","key":"11598_CR138","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1016\/j.jai.2024.02.003","volume":"3","author":"Z Ning","year":"2024","unstructured":"Ning Z, Xie L (2024) A survey on multi-agent reinforcement learning and its application. J Autom Intell 3(2):73\u201391. https:\/\/doi.org\/10.1016\/j.jai.2024.02.003","journal-title":"J Autom Intell"},{"key":"11598_CR139","doi-asserted-by":"publisher","unstructured":"Oliehoek FA, Amato C et al (2016) A concise introduction to decentralized POMDPs, vol 1. Springer. https:\/\/doi.org\/10.1007\/978-3-319-28929-8_3","DOI":"10.1007\/978-3-319-28929-8_3"},{"key":"11598_CR140","doi-asserted-by":"crossref","unstructured":"Omidshafiei S, Kapishnikov A, Assogba Y, Dixon L, Kim B (2022) Beyond rewards: a hierarchical perspective on offline multiagent behavioral analysis. In: Advances in neural information processing systems. pp 3444\u20133460","DOI":"10.52202\/068431-0249"},{"key":"11598_CR141","unstructured":"Otto F, Celik O, Zhou H, Ziesche H, Ngo VA, Neumann G (2023) Proceedings of the 6th conference on robot learning. pp 1244\u20131265"},{"key":"11598_CR142","doi-asserted-by":"publisher","unstructured":"Pandya R, Zhao M, Liu C, Simmons R, Admoni H (2024) Multi-agent strategy explanations for human-robot collaboration. In: 2024 IEEE international conference on robotics and automation (ICRA). IEEE, pp 17351\u201317357. https:\/\/doi.org\/10.1109\/icra57147.2024.10610720","DOI":"10.1109\/icra57147.2024.10610720"},{"key":"11598_CR143","unstructured":"Papoudakis G, Christianos F, Rahman A, Albrecht SV (2019) Dealing with non-stationarity in multi-agent deep reinforcement learning. arXiv preprint https:\/\/doi.org\/arXiv:1906.04737"},{"issue":"3","key":"11598_CR144","doi-asserted-by":"publisher","first-page":"670","DOI":"10.1109\/tg.2023.3346394","volume":"16","author":"K Peng","year":"2023","unstructured":"Peng K, Ma T, Yu X, Rong H, Qian Y, Al-Nabhan N (2023) Gcma: An adaptive multiagent reinforcement learning framework with group communication for complex and similar tasks coordination. IEEE Trans Games 16(3):670\u2013682. https:\/\/doi.org\/10.1109\/tg.2023.3346394","journal-title":"IEEE Trans Games"},{"key":"11598_CR145","doi-asserted-by":"crossref","unstructured":"Peng K, Li P, Hao J (2025a) Enhancing graph-based coordination with evolutionary algorithms for episodic multi-agent reinforcement learning. In: Proceedings of the 24th international conference on autonomous agents and multiagent systems. pp 1623\u20131631","DOI":"10.65109\/DRES3425"},{"key":"11598_CR146","doi-asserted-by":"crossref","unstructured":"Peng K, Zhu S, Ma T (2025b) Stpe-marl: Spatio-temporal multi-agent population evolution reinforcement learning. ACM Trans Intell Syst Technol","DOI":"10.1145\/3742479"},{"issue":"2","key":"11598_CR147","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/s10994-022-06286-6","volume":"112","author":"E Pesce","year":"2023","unstructured":"Pesce E, Montana G (2023) Learning multi-agent coordination through connectivity-driven communication. Mach Learn 112(2):483\u2013514. https:\/\/doi.org\/10.1007\/s10994-022-06286-6","journal-title":"Mach Learn"},{"issue":"3","key":"11598_CR148","doi-asserted-by":"publisher","first-page":"3769","DOI":"10.1109\/tnnls.2022.3197918","volume":"35","author":"S Qi","year":"2022","unstructured":"Qi S, Huang X, Peng P, Huang X, Zhang J, Wang X (2022) Cascaded attention: adaptive and gated graph attention network for multiagent reinforcement learning. IEEE Trans Neural Netw Learn Syst 35(3):3769\u20133779. https:\/\/doi.org\/10.1109\/tnnls.2022.3197918","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"11598_CR149","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2021.118403","volume":"309","author":"D Qiu","year":"2022","unstructured":"Qiu D, Dong Z, Zhang X et al (2022) Safe reinforcement learning for real-time automatic control in a smart energy-hub. Appl Energy 309:118403","journal-title":"Appl Energy"},{"issue":"2","key":"11598_CR150","doi-asserted-by":"publisher","first-page":"3401","DOI":"10.1109\/TPWRS.2023.3276827","volume":"39","author":"D Qiu","year":"2023","unstructured":"Qiu D, Wang Y, Wang J, Zhang N, Strbac G, Kang C (2023) Resilience-oriented coordination of networked microgrids: a Shapley q-value learning approach. IEEE Trans Power Syst 39(2):3401\u20133416","journal-title":"IEEE Trans Power Syst"},{"key":"11598_CR151","doi-asserted-by":"publisher","unstructured":"Radke D, Larson K, Brecht T (2023) The importance of credo in multiagent learning. In: Proceedings of the 2023 international conference on autonomous agents and multiagent systems. International Foundation for Autonomous Agents and Multiagent Systems. Richland, SC, AAMAS, pp 1\u20139. https:\/\/doi.org\/10.5555\/3545946.3598902","DOI":"10.5555\/3545946.3598902"},{"key":"11598_CR152","unstructured":"Reiestad E (2025) Better together? Explaining emergent behavior in multi-agent reinforcement learning. Master\u2019s thesis, NTNU"},{"issue":"1","key":"11598_CR153","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1631\/fitee.22e0073","volume":"24","author":"Y Ren","year":"2023","unstructured":"Ren Y, Ye Z, Chen Y, Jiang X, Song G (2023) Soft-hgrns: soft hierarchical graph recurrent networks for multi-agent partially observable environments. Front Inf Technol Electron Eng 24(1):117\u2013130. https:\/\/doi.org\/10.1631\/fitee.22e0073","journal-title":"Front Inf Technol Electron Eng"},{"key":"11598_CR154","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121111","volume":"235","author":"F Ren","year":"2024","unstructured":"Ren F, Dong W, Zhao X, Zhang F, Kong Y, Yang Q (2024a) Two-layer coordinated reinforcement learning for traffic signal control in traffic network. Expert Syst Appl 235:121111. https:\/\/doi.org\/10.1016\/j.eswa.2023.121111 (https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0957417423016135)","journal-title":"Expert Syst Appl"},{"issue":"10","key":"11598_CR155","doi-asserted-by":"publisher","first-page":"12021","DOI":"10.1109\/tii.2024.3413356","volume":"20","author":"Y Ren","year":"2024","unstructured":"Ren Y, Zhang H, Du L, Zhang Z, Zhang J, Li H (2024b) Stealthy black-box attack with dynamic threshold against marl-based traffic signal control system. IEEE Trans Ind Inf 20(10):12021\u201312031. https:\/\/doi.org\/10.1109\/tii.2024.3413356","journal-title":"IEEE Trans Ind Inf"},{"key":"11598_CR156","doi-asserted-by":"crossref","unstructured":"Ribeiro MT, Singh S, Guestrin C (2018) Anchors: High-precision model-agnostic explanations. In: Proceedings of the AAAI conference on artificial intelligence. p 32","DOI":"10.1609\/aaai.v32i1.11491"},{"key":"11598_CR157","doi-asserted-by":"crossref","unstructured":"Roghani S, Koyuncu E (2025) An explainable and fair hierarchical rl-based alternative trajectory proposal framework for autonomous u-plan approval in u-space. In: 2025 Integrated communications, navigation and surveillance conference (ICNS). IEEE, pp 1\u201313","DOI":"10.1109\/ICNS65417.2025.10976800"},{"issue":"4","key":"11598_CR158","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3502868","volume":"31","author":"A Romdhana","year":"2022","unstructured":"Romdhana A, Merlo A, Ceccato M, Tonella P (2022) Deep reinforcement learning for black-box testing of android apps. ACM Trans Softw Eng Methodol (TOSEM) 31(4):1\u201329","journal-title":"ACM Trans Softw Eng Methodol (TOSEM)"},{"key":"11598_CR159","doi-asserted-by":"crossref","unstructured":"Ruan J, Hao X, Li D, Mao H (2023) Learning to collaborate by grouping: a consensus-oriented strategy for multi-agent reinforcement learning. https:\/\/doi.org\/arXiv:2307.1553010.3233\/faia230493 arXiv preprint","DOI":"10.3233\/FAIA230493"},{"key":"11598_CR160","doi-asserted-by":"crossref","unstructured":"Ruan J, Xie R, Xiong X, Xu S, Xu B (2024) Made: Multi-scale decision enhancement for multi-agent reinforcement learning. In: ICASSP 2024\u20132024 IEEE international conference on acoustics. IEEE, Speech and Signal Processing (ICASSP), pp 31\u201335","DOI":"10.1109\/ICASSP48485.2024.10447913"},{"key":"11598_CR161","doi-asserted-by":"publisher","unstructured":"Schier M, Schubert F, Rosenhahn B (2025) Explainable reinforcement learning via dynamic mixture policies. In: 2025 IEEE international conference on robotics and automation (ICRA), pp. To be published. https:\/\/doi.org\/10.1109\/icra55743.2025.11127782","DOI":"10.1109\/icra55743.2025.11127782"},{"key":"11598_CR162","doi-asserted-by":"publisher","first-page":"48004","DOI":"10.2139\/ssrn.4506843","volume":"12","author":"T Selimovi\u0107","year":"2024","unstructured":"Selimovi\u0107 T, Peti M, Bogdan S (2024) Multi-agent active perception based on reinforcement learning and pomdp. IEEE Access 12:48004\u201348016. https:\/\/doi.org\/10.2139\/ssrn.4506843","journal-title":"IEEE Access"},{"key":"11598_CR163","doi-asserted-by":"crossref","unstructured":"Selmonaj A, Antonucci A, Schneider A, R\u00fcegsegger M, Sommer M (2025a) Explaining strategic decisions in multi-agent reinforcement learning for aerial combat tactics. arXiv preprint arXiv:2505.11311","DOI":"10.14339\/STO-MSG-217-05"},{"key":"11598_CR164","doi-asserted-by":"crossref","unstructured":"Selmonaj A, Strupl M, Szehr O, Antonucci A (2025b) Understanding action effects through instrumental empowerment in multi-agent reinforcement learning. https:\/\/doi.org\/arXiv:2508.1565210.3233\/faia250947 arXiv preprint","DOI":"10.3233\/FAIA250947"},{"key":"11598_CR165","doi-asserted-by":"publisher","unstructured":"Shah AB, Wen Y, Chen J, Wu X, Fu X (2024) Safe offline-to-online multi-agent decision transformer: a safety conscious sequence modeling approach. In: 2024 IEEE\/RSJ international conference on intelligent robots and systems (IROS). IEEE, pp 12400\u201312407. https:\/\/doi.org\/10.1109\/iros58592.2024.10801292","DOI":"10.1109\/iros58592.2024.10801292"},{"key":"11598_CR166","doi-asserted-by":"publisher","first-page":"5711","DOI":"10.52202\/068431-0413","volume":"35","author":"J Shao","year":"2022","unstructured":"Shao J, Lou Z, Zhang H, Jiang Y, He S, Ji X (2022) Self-organized group for cooperative multi-agent reinforcement learning. Adv Neural Inf Process Syst 35:5711\u20135723","journal-title":"Adv Neural Inf Process Syst"},{"key":"11598_CR167","doi-asserted-by":"crossref","unstructured":"Sharma PK, Zaroukian E, Asher DE, Howell B (2022) Emergent behaviors in multi-agent target acquisition. In: Artificial intelligence and machine learning for multi-domain operations applications IV, SPIE. pp 361\u2013371","DOI":"10.1117\/12.2618646"},{"issue":"2","key":"11598_CR168","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1007\/s10458-022-09580-8","volume":"36","author":"J Sheng","year":"2022","unstructured":"Sheng J, Wang X, Jin B, Yan J, Li W, Chang TH, Wang J, Zha H (2022) Learning structured communication for multi-agent reinforcement learning. Auton Agent Multi-Agent Syst 36(2):50. https:\/\/doi.org\/10.1007\/s10458-022-09580-8","journal-title":"Auton Agent Multi-Agent Syst"},{"key":"11598_CR169","unstructured":"Shi S, Zhang Y, Leibo JZ, Du Y (2025) Resolving complex social dilemmas by aligning preferences with counterfactual regret. openreview.net\/forum?id=CgkGFeSpo0, openreview.net\/pdf?id=CgkGFeSpo0.(iCLR 2025 OpenReview)"},{"key":"11598_CR170","doi-asserted-by":"crossref","unstructured":"Soul\u00e9 J, Jamont JP, Occello M, Traonouez LM, Th\u00e9ron P (2025a) An organizationally-oriented approach to enhancing explainability and control in multi-agent reinforcement learning. In: Proceedings of the international joint conference on autonomous agents and multiagent systems. pp 1968\u20131976","DOI":"10.65109\/OHJD5218"},{"key":"11598_CR171","doi-asserted-by":"crossref","unstructured":"Soul\u00e9 J, Jamont JP, Occello M, Traonouez LM, Th\u00e9ron P (2025b) Streamlining resilient Kubernetes autoscaling with multi-agent systems via an automated online design framework. https:\/\/doi.org\/arXiv:2505.2155910.1109\/cloud67622.2025.00015 arXiv preprint","DOI":"10.1109\/CLOUD67622.2025.00015"},{"issue":"27","key":"11598_CR172","doi-asserted-by":"publisher","first-page":"19765","DOI":"10.1007\/s00521-023-08784-7","volume":"35","author":"Z Sun","year":"2023","unstructured":"Sun Z, Wu H, Shi Y, Yu X, Gao Y, Pei W, Yang Z, Piao H, Hou Y (2023) Multi-agent air combat with two-stage graph-attention communication. Neural Comput Appl 35(27):19765\u201319781. https:\/\/doi.org\/10.1007\/s00521-023-08784-7","journal-title":"Neural Comput Appl"},{"key":"11598_CR173","unstructured":"Sundararajan M, Taly A, Yan Q (2017) Axiomatic attribution for deep networks. In: Proceedings of the international conference on machine learning. pp 3319\u20133328"},{"key":"11598_CR174","doi-asserted-by":"crossref","unstructured":"Sunehag P, Lever G, Gruslys A, Czarnecki WM, Zambaldi V, Jaderberg M, Lanctot M, Sonnerat N, Leibo JZ, Tuyls K (2017) Value-decomposition networks for cooperative multi-agent learning. https:\/\/doi.org\/arXiv:1706.0529610.1016\/j.neunet.2025.107692 arXiv preprint","DOI":"10.65109\/JSRC7365"},{"key":"11598_CR175","doi-asserted-by":"publisher","unstructured":"Su D, Peng H, Zeng G, Li P, Li A, Pan Y (2025) Emergence of cooperation in multi-agent reinforcement learning via coalition labeling and structural entropy. In: Proceedings of the 2025 SIAM international conference on data mining (SDM), SIAM. pp 507\u2013515. https:\/\/doi.org\/10.1137\/1.9781611978520.55","DOI":"10.1137\/1.9781611978520.55"},{"key":"11598_CR176","unstructured":"Tabrez A, Luebbers MB, Ruvane K, Rabin AH, King KW, Gerichs W, Hayes B (2024) Hierarchical multi-agent reinforcement learning with explainable decision support for human-robot teams. In: Proceedings of the ACM\/IEEE international conference on human-robot interaction. Boulder, CO, USA, (hRI '24)"},{"key":"11598_CR177","doi-asserted-by":"publisher","unstructured":"Taghavi M, Farnoosh R (2025a) Quantum computing and neuromorphic computing for safe, reliable, and explainable multi-agent reinforcement learning: Optimal control in autonomous robotics. Iran J Comput Sci 1\u201317. https:\/\/doi.org\/10.1007\/s42044-025-00306-z","DOI":"10.1007\/s42044-025-00306-z"},{"key":"11598_CR178","unstructured":"Taghavi M, Farnoosh R (2025b) Latent variable modeling in multi-agent reinforcement learning via expectation-maximization for uav-based wildlife protection. https:\/\/doi.org\/arXiv:2509.02579arXiv preprint Preprint at https:\/\/doi.org\/arxiv.org\/abs\/2509.02579"},{"key":"11598_CR179","doi-asserted-by":"crossref","unstructured":"Takagi Y, Tabalba R, Kirshenbaum N, Leigh J (2024) Abstracted trajectory visualization for explainability in reinforcement learning. In: 2024 IEEE conference on artificial intelligence (CAI). IEEE, pp 75\u201382","DOI":"10.1109\/CAI59869.2024.00023"},{"key":"11598_CR180","unstructured":"Tesic M, Zhao Y, Leibo JZ, Trivedi RS, Hernandez-Orallo J (2025) Beyond the high score. In: Prosocial ability profiles of multi-agent populations. arXiv preprint https:\/\/doi.org\/arXiv:2509.14485"},{"key":"11598_CR181","doi-asserted-by":"crossref","unstructured":"Thakre B, Yadav U, Bondre SV (2025) Deep reinforcement learning in healthcare and biomedical application. Innov Biomed Eng. Academic Press, pp 241\u2013299","DOI":"10.1016\/B978-0-443-30146-9.00008-3"},{"issue":"11","key":"11598_CR182","doi-asserted-by":"publisher","first-page":"4793","DOI":"10.1109\/TNNLS.2020.3027314","volume":"32","author":"E Tjoa","year":"2020","unstructured":"Tjoa E, Guan C (2020) A survey on explainable artificial intelligence (xai): toward medical xai. IEEE Trans Neural Netw Learn Syst 32(11):4793\u20134813","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"11598_CR183","doi-asserted-by":"crossref","unstructured":"Toquebiau M, Jun JY, Benamar F, Bredeche N (2025) Towards language-augmented multi-agent deep reinforcement learning. https:\/\/doi.org\/arXiv:2506.05236 arXiv preprint Preprint at https:\/\/doi.org\/arxiv.org\/abs\/2506.05236","DOI":"10.3233\/FAIA251260"},{"key":"11598_CR184","doi-asserted-by":"crossref","unstructured":"Towers M, Du Y, Freeman C, Norman TJ (2024) Explaining an agent\u015b future beliefs through temporally decomposing future reward estimators. arXiv preprint arXiv:2408.08230","DOI":"10.3233\/FAIA240814"},{"key":"11598_CR185","doi-asserted-by":"crossref","unstructured":"Vos D, Verwer S (2023) Optimal decision tree policies for Markov decision processes. https:\/\/doi.org\/arXiv:2301.1318510.24963\/ijcai.2023\/606 arXiv preprint","DOI":"10.24963\/ijcai.2023\/606"},{"key":"11598_CR186","doi-asserted-by":"crossref","unstructured":"Wai KP, Geng M, Pateria S, Subagdja B, Tan AH (2024) Explaining sequences of actions in multi-agent deep reinforcement learning models. In: Proceedings of the 23rd international conference on autonomous agents and multiagent systems. pp 2537\u20132539","DOI":"10.65109\/YLON4709"},{"key":"11598_CR190","doi-asserted-by":"crossref","unstructured":"Wang C, Aouf N (2024) Explainable deep adversarial reinforcement learning approach for robust autonomous driving. In: IEEE transactions on intelligent vehicles","DOI":"10.1109\/TIV.2024.3379367"},{"key":"11598_CR187","doi-asserted-by":"publisher","first-page":"3271","DOI":"10.2139\/ssrn.5371728","volume":"34","author":"J Wang","year":"2021","unstructured":"Wang J, Xu W, Gu Y, Song W, Green TC (2021) Multi-agent reinforcement learning for active voltage control on power distribution networks. Adv Neural Inf Process Syst 34:3271\u20133284. https:\/\/doi.org\/10.2139\/ssrn.5371728","journal-title":"Adv Neural Inf Process Syst"},{"issue":"1","key":"11598_CR188","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/JAS.2023.123843","volume":"11","author":"D Wang","year":"2023","unstructured":"Wang D, Gao N, Liu D, Li J, Lewis FL (2023) Recent progress in reinforcement learning and adaptive dynamic programming for advanced control applications. IEEE\/CAA J Automatica Sinica 11(1):18\u201336","journal-title":"IEEE\/CAA J Automatica Sinica"},{"key":"11598_CR189","doi-asserted-by":"crossref","unstructured":"Wang D, Antoniades A, Luong KD, Zhang E, Kosan M, Li J, Singh A, Wang WY, Li L (2024) Global human-guided counterfactual explanations for molecular properties via reinforcement learning. In: Proceedings of the 30th ACM SIGKDD conference on knowledge discovery and data mining. pp 2991\u20133000","DOI":"10.1145\/3637528.3672045"},{"key":"11598_CR191","unstructured":"Wang Z, Du Y, Zhang Y, Fang M, Huang B (2025a) Macca: Offline multi-agent reinforcement learning with causal credit assignment. Trans Mach Learn Res"},{"key":"11598_CR192","unstructured":"Wang Z, Zhang Z, Fang F, Du Y (2025b) M3HF: Multi-agent reinforcement learning from multi-phase human feedback of mixed quality. In: Proceedings of machine learning research. pp 65429\u201365448"},{"key":"11598_CR193","doi-asserted-by":"publisher","unstructured":"Wan K, Liu Y, Liu H, Xu X (2025a) A framework for modeling cognitive processes in intelligent agents using behavior trees. In: Proceedings of the 2025 5th international conference on internet of things and machine learning. pp 267\u2013271. https:\/\/doi.org\/10.1145\/3749566.3749619","DOI":"10.1145\/3749566.3749619"},{"key":"11598_CR194","doi-asserted-by":"crossref","unstructured":"Wan Z, Li Y, Wen X, Song Y, Wang H, Yang L, Schmidt M, Wang J, Zhang W, Hu S (2025b) Rema: Learning to meta-think for llms with multi-agent reinforcement learning. https:\/\/doi.org\/arXiv:2503.0950110.48550\/arXiv.2503.09501 arXiv preprint","DOI":"10.52202\/085713-4225"},{"issue":"1","key":"11598_CR195","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1109\/tnnls.2022.3172572","volume":"35","author":"Q Wei","year":"2022","unstructured":"Wei Q, Li Y, Zhang J, Wang FY (2022) Vgn: Value decomposition with graph attention networks for multiagent reinforcement learning. IEEE Trans Neural Netw Learn Syst 35(1):182\u2013195. https:\/\/doi.org\/10.1109\/tnnls.2022.3172572","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"11598_CR196","doi-asserted-by":"publisher","unstructured":"Wei Y, Shan X, Miao R, Li J (2025) Lero: Llm-driven evolutionary framework with hybrid rewards and enhanced observation for multi-agent reinforcement learning. In: International conference on intelligent computing. Springer, pp 15\u201326. https:\/\/doi.org\/10.1007\/978-981-96-9894-3_2","DOI":"10.1007\/978-981-96-9894-3_2"},{"key":"11598_CR197","doi-asserted-by":"publisher","unstructured":"Wenhan Y, Qian L, Chua TJ, Zhao J (2024) Counterfactual reward estimation for credit assignment in multi-agent deep reinforcement learning over wireless video transmission. In: 2024 IEEE 44th international conference on distributed computing systems (ICDCS). IEEE, pp 1177\u20131189. https:\/\/doi.org\/10.1109\/icdcs60910.2024.00112","DOI":"10.1109\/icdcs60910.2024.00112"},{"issue":"2","key":"11598_CR198","doi-asserted-by":"publisher","first-page":"728","DOI":"10.1109\/LRA.2022.3231497","volume":"8","author":"H Wu","year":"2022","unstructured":"Wu H, Ghadami A, Bayrak AE, Smereka JM, Epureanu BI (2022) Evaluating emergent coordination in multi-agent task allocation through causal inference and sub-team identification. IEEE Robot Automat Lett 8(2):728\u2013735","journal-title":"IEEE Robot Automat Lett"},{"key":"11598_CR199","doi-asserted-by":"crossref","unstructured":"Xiao B, Ramasubramanian B, Poovendran R (2022) Agent-temporal attention for reward redistribution in episodic multi-agent reinforcement learning. In: Proceedings of the international joint conference on autonomous agents and multiagent systems. pp 1391\u20131399","DOI":"10.65109\/TVAW9016"},{"key":"11598_CR200","unstructured":"Xie T, Gao Z, Ren Q, Luo H, Hong Y, Dai B, Zhou J, Qiu K, Wu Z, Luo C (2025) Logic-rl: Unleashing llm reasoning with rule-based reinforcement learning. https:\/\/doi.org\/arXiv:2502.1476810.48550\/arXiv.2502.14768 arXiv preprint"},{"key":"11598_CR201","unstructured":"Xi-Jia Z, Guo Y, Chen S, Stepputtis S, Gombolay M, Sycara K, Campbell J (2025) Model-agnostic policy explanations with large language models. https:\/\/doi.org\/arXiv:2504.0562510.48550\/arXiv.2504.05625 arXiv preprint"},{"key":"11598_CR202","doi-asserted-by":"publisher","unstructured":"Xiong Y, Hu Z, Huang Y, Wu R, Guan K, Fang X, Jiang J, Zhou T, Hu Y, Liu H (2024) Xrl-bench:a benchmark for evaluating and comparing explainable reinforcement learning techniques. In: proceedings of the 30th ACM SIGKDD conference on knowledge discovery and data mining. pp 6073\u20136082. https:\/\/doi.org\/10.1145\/3637528.3671595","DOI":"10.1145\/3637528.3671595"},{"key":"11598_CR204","doi-asserted-by":"crossref","unstructured":"Xu Z, Bai Y, Zhang B, Li D, Fan G (2023) Haven: Hierarchical cooperative multi-agent reinforcement learning with dual coordination mechanism. In: Proceedings of the AAAI conference on artificial intelligence. pp 11735\u201311743","DOI":"10.1609\/aaai.v37i10.26386"},{"issue":"7","key":"11598_CR203","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-023-3987-y","volume":"67","author":"X Xu","year":"2024","unstructured":"Xu X, Wu F, Bilal M, Xia X, Dou W, Yao L, Zhong W (2024) Xrl-shap-cache: an explainable reinforcement learning approach for intelligent edge service caching in content delivery networks. Sci China Inf Sci 67(7):170303. https:\/\/doi.org\/10.1007\/s11432-023-3987-y","journal-title":"Sci China Inf Sci"},{"key":"11598_CR205","doi-asserted-by":"publisher","unstructured":"Yang M, Zhao K, Wang Y, Dong R, Du Y, Liu F, Zhou M, U LH, (2024) Team-wise effective communication in multi-agent reinforcement learning. Auton Agent Multi-Agent Syst 38(2):36. https:\/\/doi.org\/10.1007\/s10458-024-09665-6","DOI":"10.1007\/s10458-024-09665-6"},{"issue":"12","key":"11598_CR206","doi-asserted-by":"publisher","first-page":"2361","DOI":"10.3390\/electronics14122361","volume":"14","author":"B Yang","year":"2025","unstructured":"Yang B, Gao L, Zhou F, Yao H, Fu Y, Sun Z, Tian F, Ren H (2025a) A coordination optimization framework for multi-agent reinforcement learning based on reward redistribution and experience reutilization. Electronics 14(12):2361. https:\/\/doi.org\/10.3390\/electronics14122361","journal-title":"Electronics"},{"key":"11598_CR207","unstructured":"Yang S, Hu H, Shi E, Zhang S (2025b) Dual-level behavioral consistency for inter-group and intra-group coordination in multi-agent systems. arXiv preprint arXiv:2506.18651"},{"key":"11598_CR208","doi-asserted-by":"publisher","unstructured":"Yang H, Shi D, Xie JS, Chen G, Qiu Y, Yang C, S (2025c) Acting beyond learning: Imagination-assisted decision-making in the visual-based multi-agent cooperative scenarios. In: Proceedings of the AAAI conference on artificial intelligence. pp 21947\u201321955. https:\/\/doi.org\/10.1609\/aaai.v39i20.35502","DOI":"10.1609\/aaai.v39i20.35502"},{"key":"11598_CR209","doi-asserted-by":"publisher","unstructured":"Yao D, Sun C, Li K, Zhou K, Li H, Wang R, Liu L (2024) Cmix: Causal value decomposition for cooperative multi-agent reinforcement learning. In: 2024 IEEE international conference on systems, man, and cybernetics. IEEE, pp 4105\u20134112. https:\/\/doi.org\/10.1109\/smc54092.2024.10831507","DOI":"10.1109\/smc54092.2024.10831507"},{"key":"11598_CR210","doi-asserted-by":"crossref","unstructured":"Yoo B, Shin Y, Kim H, Yang CE, J (2025) Adaptive episode length adjustment for multi-agent reinforcement learning. In: Proceedings of the international joint conference on autonomous agents and multiagent systems. pp 2253\u20132261","DOI":"10.65109\/LBZV4021"},{"key":"11598_CR211","doi-asserted-by":"publisher","unstructured":"Yuan L, Wang J, Zhang F, Wang C, Zhang Z, Yu Y, Zhang C (2022) Multi-agent incentive communication via decentralized teammate modeling. In: Proceedings of the AAAI conference on artificial intelligence. pp 9466\u20139474. https:\/\/doi.org\/10.1609\/aaai.v36i9.21179","DOI":"10.1609\/aaai.v36i9.21179"},{"key":"11598_CR212","unstructured":"Zabounidis R, Campbell J, Stepputtis S, Hughes D, Sycara KP (2023) Concept learning for interpretable multi-agent reinforcement learning. In: Conference on robot learning, PMLR. pp 1828\u20131837"},{"key":"11598_CR219","doi-asserted-by":"crossref","unstructured":"Zhang Q, Xu B (2024) Towards zero-shot generalization: mutual information-guided hierarchical multi-agent coordination. In: 2024 International joint conference on neural networks (IJCNN). IEEE, pp 1\u20139","DOI":"10.1109\/IJCNN60899.2024.10651259"},{"key":"11598_CR218","doi-asserted-by":"publisher","unstructured":"Zhang H, Li G, Liu CH, Wang G, Tang J (2023) Himacmic: hierarchical multi-agent deep reinforcement learning with dynamic asynchronous macro strategy. In: Proceedings of the 29th ACM SIGKDD conference on knowledge discovery and data mining. pp 3239\u20133248. https:\/\/doi.org\/10.1145\/3580305.3599379","DOI":"10.1145\/3580305.3599379"},{"key":"11598_CR213","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2024.3392587","author":"Y Zhang","year":"2024","unstructured":"Zhang Y, Zheng G, Liu Z, Li Q, Zeng H (2024a) Marlens: understanding multi-agent reinforcement learning for traffic signal control via visual analytics. IEEE Trans Visual Comput Graph. https:\/\/doi.org\/10.1109\/tvcg.2024.3392587","journal-title":"IEEE Trans Visual Comput Graph"},{"key":"11598_CR217","unstructured":"Zhang Y, Du Y, Huang B, Fang M, Pechenizkiy M (2024b) A causality-inspired spatial-temporal return decomposition approach for multi-agent reinforcement learning. In: NeurIPS 2024 causal representation learning workshop, openreview.net\/pdf?id=tlNkThyt18"},{"issue":"8","key":"11598_CR214","doi-asserted-by":"publisher","first-page":"881","DOI":"10.1007\/s11227-025-07377-6","volume":"81","author":"Q Zhang","year":"2025","unstructured":"Zhang Q, Wang P, Ni C, Rong W, Ren C, Liu X, Shan H (2025a) Comp-lg: coordinate-aware multi-agent pathfinding via learnable communication graphs. J Supercomput 81(8):881. https:\/\/doi.org\/10.1007\/s11227-025-07377-6","journal-title":"J Supercomput"},{"key":"11598_CR215","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.127717","author":"M Zhang","year":"2025","unstructured":"Zhang M, Fang Z, Wang T, Lu S, Wang X, Shi T (2025b) Ccma: A framework for cascading cooperative multi-agent in autonomous driving merging using large language models. Expert Syst Appl. https:\/\/doi.org\/10.1016\/j.eswa.2025.127717","journal-title":"Expert Syst Appl"},{"key":"11598_CR216","unstructured":"Zhang Z, Cheng B, Wang Z, Zhou Y, Li G, Lu P, He B, Chen J (2025c) Pagnet: Pluggable adaptive generative networks for information completion in multi-agent communication. arXiv preprint arXiv:2502.03845 Preprint at https:\/\/arxiv.org\/abs\/2502.03845"},{"key":"11598_CR220","doi-asserted-by":"publisher","unstructured":"Zhao X, Xie Y (2025) Multi-level advantage credit assignment for cooperative multi-agent reinforcement learning. In: The 28th international conference on artificial intelligence and statistics. https:\/\/doi.org\/10.3390\/app12146938","DOI":"10.3390\/app12146938"},{"key":"11598_CR221","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106432","volume":"178","author":"T Zhu","year":"2024","unstructured":"Zhu T, Shi X, Xu X, Gui J, Cao J (2024) Hypercomm: Hypergraph-based communication in multi-agent reinforcement learning. Neural Netw 178:106432. https:\/\/doi.org\/10.1016\/j.neunet.2024.106432","journal-title":"Neural Netw"},{"key":"11598_CR222","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-025-11272-9","volume-title":"Neural Comput Appl","author":"C Zhu","year":"2025","unstructured":"Zhu C, Dastani M, Wang S (2025) Communication with factorized policy gradients in multi-agent deep reinforcement learning. Neural Comput Appl. https:\/\/doi.org\/10.1007\/s00521-025-11272-9"},{"key":"11598_CR223","doi-asserted-by":"publisher","unstructured":"Zhuang Z, Lu CY, Chang Y, Wang YK, Do T, Lin CT (2025) Aegis: Human attention-based explainable guidance for intelligent vehicle systems. In: Proceedings of the 2025 CHI conference on human factors in computing systems. pp 1\u201319. https:\/\/doi.org\/10.1145\/3706598.3713779","DOI":"10.1145\/3706598.3713779"}],"container-title":["Artificial Intelligence Review"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10462-026-11598-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-026-11598-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-026-11598-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T00:40:58Z","timestamp":1791160858000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10462-026-11598-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,13]]},"references-count":223,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,10]]}},"alternative-id":["11598"],"URL":"https:\/\/doi.org\/10.1007\/s10462-026-11598-3","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-7965328\/v1","asserted-by":"object"}]},"ISSN":["1573-7462"],"issn-type":[{"value":"1573-7462","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,13]]},"assertion":[{"value":"28 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors have no relevant financial or non-financial interests to disclose.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable, as this is a review article and does not involve any new studies with human or animal subjects.","order":2,"name":"Ethics","label":"Ethical approval and consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable, as this article contains no personally identifiable information.","order":3,"name":"Ethics","label":"Consent for publication","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"209"}}