{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T20:20:01Z","timestamp":1783110001705,"version":"3.54.6"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819543663","type":"print"},{"value":"9789819543670","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T00:00:00Z","timestamp":1763769600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T00:00:00Z","timestamp":1763769600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-4367-0_40","type":"book-chapter","created":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T12:38:36Z","timestamp":1763728716000},"page":"597-610","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["An Ensemble Method with\u00a0Plans-Managed Policy for\u00a0Proximal Policy Optimization"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1011-9829","authenticated-orcid":false,"given":"Tianshu","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7348-366X","authenticated-orcid":false,"given":"Yanran","family":"Guan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1796-8013","authenticated-orcid":false,"given":"Zinovi","family":"Rabinovich","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,22]]},"reference":[{"key":"40_CR1","doi-asserted-by":"crossref","unstructured":"Blanco-Volle, C., Verstaevel, N., Combettes, S., Gleizes, M., Seixas, M.P.: Explainability and interpretability of an ensemble multi-agent system for supervised learning. In: Proceedings of the International Conference on Principles and Practice of Multi-Agent Systems, pp. 335\u2013350 (2024)","DOI":"10.1007\/978-3-031-77367-9_26"},{"key":"40_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113820","volume":"164","author":"S Carta","year":"2021","unstructured":"Carta, S., Ferreira, A., Podda, A.S., Recupero, D.R., Sanna, A.: Multi-DQN: an ensemble of deep q-learning agents for stock market forecasting. Expert Syst. Appl. 164, 113820 (2021)","journal-title":"Expert Syst. Appl."},{"key":"40_CR3","doi-asserted-by":"crossref","unstructured":"Chen, R., Tan, Y.: A multi-branch ensemble agent network for multi-agent reinforcement learning. In: Proceedings of the International Conference on Data Mining and Big Data, pp. 485\u2013498 (2021)","DOI":"10.1007\/978-981-16-7502-7_44"},{"issue":"1","key":"40_CR4","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1007\/s10458-024-09653-w","volume":"38","author":"M Diab","year":"2024","unstructured":"Diab, M., Demiris, Y.: A framework for trust-related knowledge transfer in human-robot interaction. Auton. Agent. Multi-Agent Syst. 38(1), 24 (2024)","journal-title":"Auton. Agent. Multi-Agent Syst."},{"key":"40_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123158","volume":"245","author":"X Du","year":"2024","unstructured":"Du, X., Chen, H., Xing, Y., Yu, P.S., He, L.: A contrastive-enhanced ensemble framework for efficient multi-agent reinforcement learning. Expert Syst. Appl. 245, 123158 (2024)","journal-title":"Expert Syst. Appl."},{"key":"40_CR6","unstructured":"Feng, L., Xing, D., Zhang, J., Pan, G.: FP3O: Enabling proximal policy optimization in multi-agent cooperation with parameter-sharing versatility. CoRR abs\/2310.05053 (2023)"},{"key":"40_CR7","doi-asserted-by":"crossref","unstructured":"Ghosh, S., Laguna, S., Lim, S.H., Wynter, L., Poonawala, H.: A deep ensemble method for multi-agent reinforcement learning: a case study on air traffic control. In: Proceedings of the International Conference on Automated Planning and Scheduling, pp. 468\u2013476 (2021)","DOI":"10.1609\/icaps.v31i1.15993"},{"key":"40_CR8","doi-asserted-by":"crossref","unstructured":"Hairi, Zhang, Z., Liu, J.: Sample and communication efficient fully decentralized MARL policy evaluation via a new approach: local TD update. In: Proceedings of the International Conference on Autonomous Agents and Multiagent Systems, pp. 789\u2013797 (2024)","DOI":"10.65109\/HUZF8553"},{"key":"40_CR9","doi-asserted-by":"crossref","unstructured":"Kim, W., Sung, Y.: Parameter sharing with network pruning for scalable multi-agent deep reinforcement learning. In: Proceedings of the International Conference on Autonomous Agents and Multiagent Systems, pp. 1942\u20131950 (2023)","DOI":"10.65109\/VUZV6508"},{"key":"40_CR10","unstructured":"Li, A.C., Florensa, C., Clavera, I., Abbeel, P.: Sub-policy adaptation for hierarchical reinforcement learning. In: Proceedings of the International Conference on Learning Representations (2020)"},{"key":"40_CR11","doi-asserted-by":"crossref","unstructured":"Li, D., Lou, N., Zhang, B., Xu, Z., Fan, G.: Adaptive parameter sharing for multi-agent reinforcement learning. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 6035\u20136039 (2024)","DOI":"10.1109\/ICASSP48485.2024.10447262"},{"key":"40_CR12","doi-asserted-by":"crossref","unstructured":"Li, D., Xu, Z., Zhang, B., Zhou, G., Zhang, Z., Fan, G.: From explicit communication to tacit cooperation: a novel paradigm for cooperative MARL. In: Proceedings of the International Conference on Autonomous Agents and Multiagent Systems, pp. 2360\u20132362 (2024)","DOI":"10.65109\/TAMH6534"},{"key":"40_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2025.107747","volume":"191","author":"S Li","year":"2025","unstructured":"Li, S., et al.: Attacking cooperative multi-agent reinforcement learning by adversarial minority influence. Neural Netw. 191, 107747 (2025)","journal-title":"Neural Netw."},{"key":"40_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2025.110889","volume":"201","author":"C Liu","year":"2025","unstructured":"Liu, C., Nie, Q.: A blockchain-based LLM-driven energy-efficient scheduling system towards distributed multi-agent manufacturing scenario of new energy vehicles within the circular economy. Comput. Indus. Eng. 201, 110889 (2025)","journal-title":"Comput. Indus. Eng."},{"key":"40_CR15","unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: Advances in Neural Information Processing Systems, pp. 6379\u20136390 (2017)"},{"issue":"1","key":"40_CR16","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1007\/s10458-024-09649-6","volume":"38","author":"KR McKee","year":"2024","unstructured":"McKee, K.R., Bai, X., Fiske, S.T.: Warmth and competence in human-agent cooperation. Auton. Agent. Multi-Agent Syst. 38(1), 23 (2024)","journal-title":"Auton. Agent. Multi-Agent Syst."},{"key":"40_CR17","doi-asserted-by":"publisher","unstructured":"A Concise Introduction to Decentralized POMDPs. SIS, Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-28929-8_9","DOI":"10.1007\/978-3-319-28929-8_9"},{"key":"40_CR18","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. CoRR abs\/1707.06347 (2017)"},{"key":"40_CR19","doi-asserted-by":"crossref","unstructured":"Standen, M., Kim, J., Szabo, C.: Adversarial machine learning attacks and defences in multi-agent reinforcement learning. ACM Comput. Surv. 57(5), 124:1\u2013124:35 (2025)","DOI":"10.1145\/3708320"},{"issue":"9","key":"40_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2024.e30697","volume":"10","author":"EH Sumiea","year":"2024","unstructured":"Sumiea, E.H., et al.: Deep deterministic policy gradient algorithm: a systematic review. Heliyon 10(9), e30697 (2024)","journal-title":"Heliyon"},{"key":"40_CR21","unstructured":"Terry, J.K., et al.: PettingZoo: Gym for multi-agent reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 15032\u201315043 (2021)"},{"key":"40_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.129343","volume":"622","author":"J Tian","year":"2025","unstructured":"Tian, J., et al.: Optimal scheduling of shared autonomous electric vehicles with multi-agent reinforcement learning: a MAPPO-based approach. Neurocomputing 622, 129343 (2025)","journal-title":"Neurocomputing"},{"issue":"9","key":"40_CR23","doi-asserted-by":"publisher","first-page":"1363","DOI":"10.3390\/electronics9091363","volume":"9","author":"NV Varghese","year":"2020","unstructured":"Varghese, N.V., Mahmoud, Q.H.: A survey of multi-task deep reinforcement learning. Electronics 9(9), 1363 (2020)","journal-title":"Electronics"},{"key":"40_CR24","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhou, J., Feng, Y., Mei, J., Chen, J., Li, S.: Dashing for the golden snitch: Multi-drone time-optimal motion planning with multi-agent reinforcement learning. CoRR abs\/2409.16720 (2024)","DOI":"10.1109\/ICRA55743.2025.11128442"},{"key":"40_CR25","doi-asserted-by":"crossref","unstructured":"Xu, H., Qu, X., Rabinovich, Z.: Spiking pitch black: Poisoning an unknown environment to attack unknown reinforcement learners. In: Proceedings of the International Conference on Autonomous Agents and Multiagent Systems, pp. 1409\u20131417 (2022)","DOI":"10.65109\/HVNN4162"},{"key":"40_CR26","doi-asserted-by":"crossref","unstructured":"Yu, C., et al.: The surprising effectiveness of PPO in cooperative multi-agent games. In: Advances in Neural Information Processing Systems, pp. 24611\u201324624 (2022)","DOI":"10.52202\/068431-1787"},{"key":"40_CR27","unstructured":"Yu, Y., Yin, Q., Zhang, J., Xu, P., Huang, K.: ADMN: Agent-driven modular network for dynamic parameter sharing in cooperative multi-agent reinforcement learning. In: Proceedings of the International Joint Conference on Artificial Intelligence, pp. 302\u2013310 (2024)"},{"key":"40_CR28","unstructured":"Zhang, K., Zhu, D., Xu, Q., Zhou, H., Zheng, C.: PPS-QMIX: Periodically parameter sharing for accelerating convergence of multi-agent reinforcement learning. CoRR abs\/2403.02635 (2024)"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-4367-0_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T19:40:44Z","timestamp":1783107644000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-4367-0_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,22]]},"ISBN":["9789819543663","9789819543670"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-4367-0_40","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,22]]},"assertion":[{"value":"22 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Okinawa","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2025.apnns.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}