{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:38:20Z","timestamp":1763192300417,"version":"3.45.0"},"reference-count":33,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11228238","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":["Mutual Information and Trajectory-Awared Reinforcement Learning for Multi-Agent Path Finding"],"prefix":"10.1109","author":[{"given":"Chuang","family":"Zhao","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Computer Science and Technology,Beijing,China"}]},{"given":"Ying","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Computer Science and Technology,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/science.1254295"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364906065378"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/socs.v10i1.18510"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v1i1.18726"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19457-3_1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2014.11.006"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v28i1.13883"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6631084"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3233\/978-1-61499-672-9-810"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1613\/jair.4171"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2014.11.001"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/63"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2903261"},{"key":"ref14","first-page":"2077","article-title":"Learning to cooperate: Application of deep reinforcement learning for online agv path finding","volume-title":"Proceedings of the 19th International Conference on autonomous agents and multiagent systems","author":"Zhang"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3062803"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989037"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461113"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342305"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811643"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340876"},{"key":"ref21","first-page":"3930","article-title":"Uneven: Universal value exploration for multi-agent reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Gupta"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i9.21179"},{"key":"ref23","first-page":"15 774","article-title":"Promoting coordination through policy regularization in multi-agent deep reinforcement learning","volume":"33","author":"Roy","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"More centralized training, still decentralized execution: Multi-agent conditional policy factorization","volume-title":"The Eleventh International Conference on Learning Representations","author":"Wang","key":"ref24"},{"key":"ref25","first-page":"11 853","article-title":"Learning implicit credit assignment for cooperative multi-agent reinforcement learning","volume":"33","author":"Zhou","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref26","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume-title":"International conference on machine learning","author":"Iqbal"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2021.1998695"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3026638"},{"article-title":"Delay-aware multi-agent reinforcement learning for cooperative and competitive environments","year":"2020","author":"Chen","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.04.028"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560748"},{"article-title":"Exploration in deep reinforcement learning: a comprehensive survey","year":"2021","author":"Yang","key":"ref32"},{"key":"ref33","first-page":"507","article-title":"Agent57: Outperforming the atari human benchmark","volume-title":"International conference on machine learning","author":"Badia"}],"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\/11228238.pdf?arnumber=11228238","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:34:11Z","timestamp":1763192051000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228238\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228238","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}