{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:18:03Z","timestamp":1763191083497,"version":"3.45.0"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11228733","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["AdaPT: Adaptive Policy Transfer for Multi-agent Reinforcement Learning with Domain Classifiers"],"prefix":"10.1109","author":[{"given":"Yuxiang","family":"Mai","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiyue","family":"Yin","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wancheng","family":"Ni","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaiqi","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1101","article-title":"Coordinating multi-agent reinforcement learning with limited communication","volume-title":"Proceedings of the 2013 international conference on Autonomous agents and multi-agent systems","author":"Zhang"},{"article-title":"The starcraft multi-agent challenge","year":"2019","author":"Samvelyan","key":"ref2"},{"article-title":"Value-decomposition networks for cooperative multi-agent learning","year":"2017","author":"Sunehag","key":"ref3"},{"key":"ref4","first-page":"4295","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Rashid"},{"article-title":"Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"Proceedings of the 31st International Conference on Machine Learning, Proceedings of Machine Learning Research. PMLR","author":"Hostallero","key":"ref5"},{"key":"ref6","first-page":"10 757","article-title":"Multi-agent determinantal q-learning","volume-title":"International Conference on Machine Learning","author":"Yang"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/PERCOMW.2019.8730844"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968478"},{"article-title":"Learning transferable cooperative behavior in multi-agent teams","year":"2019","author":"Agarwal","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6221"},{"article-title":"Updet: Universal multi-agent reinforcement learning via policy decoupling with transformers","year":"2021","author":"Hu","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01155"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00900"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.144"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.358"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.806"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"article-title":"Cooperative multi-agent transfer learning with level-adaptive credit assignment","year":"2021","author":"Zhou","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/65"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0176"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553508"},{"volume-title":"Modeling purposeful adaptive behavior with the principle of maximum causal entropy","year":"2010","author":"Ziebart","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9816.003.0050"},{"article-title":"Reinforcement learning and control as probabilistic inference: Tutorial and review","year":"2018","author":"Levine","key":"ref25"},{"article-title":"Off-dynamics reinforcement learning: Training for transfer with domain classifiers","year":"2020","author":"Eysenbach","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11396"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-29946-9_25"},{"key":"ref29","first-page":"242","article-title":"Multiagent reinforcement learning: theoretical framework and an algorithm","volume-title":"ICML","volume":"98","author":"Hu"},{"key":"ref30","article-title":"Evolutionary population curriculum for scaling multi-agent reinforcement learning","volume-title":"Ph.D. dissertation","author":"Qian","year":"2020"},{"key":"ref31","first-page":"753","article-title":"Learning in multi-agent systems with sparse interactions by knowledge transfer and game abstraction","volume-title":"AAMAS","author":"Hu"},{"key":"ref32","first-page":"468","article-title":"Measuring the distance between finite markov decision processes","volume-title":"Proceedings of the 2016 international conference on autonomous agents & multiagent systems","author":"Song"},{"key":"ref33","first-page":"162","article-title":"Metrics for finite markov decision processes","volume-title":"UAI","volume":"4","author":"Ferns"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.64434\/tml.20251027"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref36","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"International Conference on Machine Learning","author":"Haarnoja"},{"key":"ref37","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja"},{"key":"ref38","first-page":"12 491","article-title":"Fop: Factorizing optimal joint policy of maximum-entropy multi-agent reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Zhang"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.01.031"},{"article-title":"Reformer: The efficient transformer","year":"2020","author":"Kitaev","key":"ref40"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref41"},{"article-title":"Categorical reparameterization with gumbel-softmax","year":"2016","author":"Jang","key":"ref42"},{"article-title":"Starcraft ii: A new challenge for reinforcement learning","year":"2017","author":"Vinyals","key":"ref43"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IMCEC51613.2021.9482235"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11228733.pdf?arnumber=11228733","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:14:05Z","timestamp":1763190845000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228733\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228733","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}