{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T19:12:47Z","timestamp":1764270767223,"version":"3.46.0"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Student Research Grant of Vidyasirimedhi Institute of Science and Technology (VISTEC), Thailand [RC]","award":["Bio-Inspired Robotics [PM]"],"award-info":[{"award-number":["Bio-Inspired Robotics [PM]"]}]},{"DOI":"10.13039\/501100007120","name":"King Mongkut’s Institute of Technology Ladkrabang","doi-asserted-by":"publisher","award":["2566-02-06-002, ND"],"award-info":[{"award-number":["2566-02-06-002, ND"]}],"id":[{"id":"10.13039\/501100007120","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/tai.2025.3566067","type":"journal-article","created":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T13:26:22Z","timestamp":1746105982000},"page":"3100-3114","source":"Crossref","is-referenced-by-count":0,"title":["$n$-LIPO: Framework for Diverse Cooperative Agent Generation Using Policy Compatibility"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9960-8483","authenticated-orcid":false,"given":"Rujikorn","family":"Charakorn","sequence":"first","affiliation":[{"name":"Bio-Inspired Robotics & Neural Engineering Laboratory, School of Information Science and Technology, Vidyasirimedhi Institute of Science and Technology, Rayong, Thailand"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4806-7576","authenticated-orcid":false,"given":"Poramate","family":"Manoonpong","sequence":"additional","affiliation":[{"name":"Bio-Inspired Robotics & Neural Engineering Laboratory, School of Information Science and Technology, Vidyasirimedhi Institute of Science and Technology, Rayong, Thailand"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7721-7564","authenticated-orcid":false,"given":"Nat","family":"Dilokthanakul","sequence":"additional","affiliation":[{"name":"School of Information Technology, King Mongkut’s Institute of Technology Ladkrabang, Bangkok, Thailand"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Trust region policy optimisation in multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kuba","year":"2022"},{"article-title":"The surprising effectiveness of Mappo in cooperative, multi-agent games","year":"2021","author":"Yu","key":"ref2"},{"key":"ref3","article-title":"On the utility of learning about humans for human-AI coordination","volume":"32","author":"Carroll","year":"2019","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2019.103216"},{"key":"ref5","first-page":"4399","article-title":"Other-play\u201d for zero-shot coordination","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Hu","year":"2020"},{"article-title":"Generalization in cooperative multi-agent systems","year":"2022","author":"Mahajan","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v24i1.7529"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2018.01.002"},{"key":"ref9","article-title":"On the critical role of conventions in adaptive human-AI collaboration","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shih","year":"2020"},{"key":"ref10","article-title":"Learning representations that enable generalization in assistive tasks","volume-title":"Proc. 6th Annu. Conf. Robot Learn.","author":"He","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20614-6_16"},{"key":"ref12","first-page":"1279","article-title":"Co-GAIL: Learning diverse strategies for human-robot collaboration","volume-title":"Proc. Conf. Robot Learn. (PMLR)","author":"Wang"},{"key":"ref13","first-page":"1478","article-title":"Learning to cooperate with unseen agents through meta-reinforcement learning","volume-title":"Proc. 20th Int. Conf. Auton. Agents MultiAgent Syst.","author":"Charakorn","year":"2021"},{"key":"ref14","first-page":"1560","article-title":"Evaluating the robustness of collaborative agents","volume-title":"Proc. 20th Int. Conf. Auton. Agents MultiAgent Syst., Ser. (AAMAS)","author":"Knott","year":"2021"},{"key":"ref15","first-page":"14502","article-title":"Collaborating with humans without human data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Strouse","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-022-09548-8"},{"key":"ref17","first-page":"16062","article-title":"Generalized beliefs for cooperative AI","volume-title":"Proc. Int. Conf. on Mach. Learn. (PMLR)","author":"Muglich","year":"2022"},{"key":"ref18","first-page":"447","article-title":"Towards deployment of robust cooperative AI agents: An algorithmic framework for learning adaptive policies","volume-title":"Proc. 19th Int. Conf. Auton. Agents MultiAgent Syst.","author":"Ghosh","year":"2020"},{"key":"ref19","first-page":"6187","article-title":"Scalable evaluation of multi-agent reinforcement learning with melting pot","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Leibo","year":"2021"},{"key":"ref20","first-page":"575","article-title":"Learning latent representations to influence multi-agent interaction","volume-title":"Proc. Conf. Robot Learn. (PMLR)","author":"Xie","year":"2021"},{"key":"ref21","first-page":"1132","article-title":"Influencing towards stable multi-agent interactions","volume-title":"Proc. Conf. Robot Learn. (PMLR)","author":"Wang","year":"2022"},{"key":"ref22","first-page":"1802","article-title":"Learning policy representations in multiagent systems","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Grover","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63823-8_46"},{"article-title":"Any-play: An intrinsic augmentation for zero-shot coordination","year":"2022","author":"Lucas","key":"ref24"},{"key":"ref25","first-page":"7611","article-title":"Maven: Multi-agent variational exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mahajan","year":"2019"},{"key":"ref26","first-page":"7204","article-title":"Trajectory diversity for zero-shot coordination","volume-title":"Proc. Int. Conf. on Mach. Learn. (PMLR)","author":"Lupu","year":"2021"},{"article-title":"Adaptive coordination in social embodied rearrangement","year":"2023","author":"Szot","key":"ref27"},{"article-title":"The starcraft multi-agent challenge","year":"2019","author":"Samvelyan","key":"ref28"},{"key":"ref29","article-title":"Generating diverse cooperative agents by learning incompatible policies","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Charakorn","year":"2023"},{"key":"ref30","first-page":"18050","article-title":"Effective diversity in population based reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Parker-Holder","year":"2020"},{"article-title":"Novel policy seeking with constrained optimization","year":"2020","author":"Sun","key":"ref31"},{"key":"ref32","article-title":"Discovering diverse nearly optimal policies with successor features","volume-title":"Proc. Workshop Unsupervised Reinforcement Learn. (ICML)","author":"Zahavy","year":"2021"},{"key":"ref33","article-title":"Continuously discovering novel strategies via reward-switching policy optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhou","year":"2021"},{"article-title":"Heterogeneous social value orientation leads to meaningful diversity in sequential social dilemmas","year":"2023","author":"Madhushani","key":"ref34"},{"article-title":"Diversifying AI: Towards creative chess with Alphazero","year":"2023","author":"Zahavy","key":"ref35"},{"article-title":"Illuminating search spaces by mapping elites","year":"2015","author":"Mouret","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2016.00040"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2019.8847944"},{"article-title":"Generating and adapting to diverse ad-hoc cooperation agents in Hanabi","year":"2020","author":"Canaan","key":"ref39"},{"article-title":"Discovering diverse multi-agent strategic behavior via reward randomization","year":"2021","author":"Tang","key":"ref40"},{"key":"ref41","article-title":"Learning zero-shot cooperation with humans, assuming humans are biased","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Yu","year":"2023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i5.25758"},{"key":"ref43","article-title":"Towards unifying behavioral and response diversity for open-ended learning in zero-sum games","volume":"34","author":"Liu","year":"2021","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref44","first-page":"434","article-title":"Open-ended learning in symmetric zero-sum games","volume-title":"Proc. Int. Conf. on Mach. Learn. (PMLR)","author":"Balduzzi","year":"2019"},{"key":"ref45","first-page":"8514","article-title":"Modelling behavioural diversity for learning in open-ended games","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Perez-Nieves","year":"2021"},{"article-title":"Towards robust ad hoc teamwork agents by creating diverse training teammates","year":"2022","author":"Rahman","key":"ref46"},{"key":"ref47","article-title":"Generating teammates for training robust ad hoc teamwork agents via best-response diversity","volume-title":"Proc. Trans. Mach. Learn. Research","author":"Rahman","year":"2023"},{"key":"ref48","article-title":"Diversity is all you need: Learning skills without a reward function","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Eysenbach","year":"2018"},{"article-title":"Dynamics-aware unsupervised discovery of skills","year":"2019","author":"Sharma","key":"ref49"},{"key":"ref50","first-page":"8198","article-title":"One solution is not all you need: Few-shot extrapolation via structured Maxent RL","volume":"33","author":"Kumar","year":"2020","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.04.009"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1287\/moor.27.4.819.297"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007665907178"},{"key":"ref54","first-page":"4992","article-title":"The emergence of individuality","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Jiang","year":"2021"},{"key":"ref55","first-page":"561","article-title":"Ray: A distributed framework for emerging AI applications","volume-title":"Proc. 13th USENIX Symp. Operating Syst. Design Implementation (OSDI)","author":"Moritz","year":"2018"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref58","first-page":"4295","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. on Mach. Learn. (PMLR)","author":"Rashid","year":"2018"},{"key":"ref59","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lowe","year":"2017"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1111\/tops.12525"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.2307\/2332510"},{"key":"ref62","first-page":"4369","article-title":"Off-belief learning","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Hu","year":"2021"},{"key":"ref63","article-title":"Adversarial diversity in Hanabi","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Cui","year":"2023"},{"key":"ref64","article-title":"Diverse conventions for human-AI collaboration","volume-title":"Proc. 37th Conf. on Neural Inf. Process. Syst.","author":"Sarkar","year":"2023"},{"article-title":"SmolLM-Blazingly fast and remarkably powerful","year":"2024","author":"Allal","key":"ref65"},{"article-title":"Phi-3 technical report: a highly capable language model locally on your phone","year":"2024","author":"Abdin","key":"ref66"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9078688\/11224646\/10981611.pdf?arnumber=10981611","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T19:01:14Z","timestamp":1764270074000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10981611\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":66,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tai.2025.3566067","relation":{},"ISSN":["2691-4581"],"issn-type":[{"type":"electronic","value":"2691-4581"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}