{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T16:20:01Z","timestamp":1759335601258,"version":"3.28.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"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":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10649966","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-9","source":"Crossref","is-referenced-by-count":1,"title":["Multi-agent Exploration with Sub-state Entropy Estimation"],"prefix":"10.1109","author":[{"given":"Jian","family":"Tao","sequence":"first","affiliation":[{"name":"Tsinghua University,Tsinghua Shenzhen International Graduate School"}]},{"given":"Yangkun","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua University,Tsinghua Shenzhen International Graduate School"}]},{"given":"Yang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Tsinghua Shenzhen International Graduate School"}]},{"given":"Kai","family":"Yang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Tsinghua Shenzhen International Graduate School"}]},{"given":"Xiu","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University,Tsinghua Shenzhen International Graduate School"}]}],"member":"263","reference":[{"key":"ref1","first-page":"263","article-title":"Minimax regret bounds for reinforcement learning","volume-title":"Proceedings of the 34th International Conference on Machine Learning","volume":"70","author":"Azar"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3366703"},{"article-title":"Exploration in deep reinforcement learning: a comprehensive survey","year":"2021","author":"Yang","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"article-title":"Exploration by random network distillation","year":"2018","author":"Burda","key":"ref5"},{"key":"ref6","first-page":"24 611","article-title":"The surprising effectiveness of ppo in cooperative multi-agent games","volume":"35","author":"Yu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Playing atari with deep reinforcement learning","year":"2013","author":"Mnih","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.36.823"},{"article-title":"Action noise in off-policy deep reinforcement learning: Impact on exploration and performance","year":"2022","author":"Hollenstein","key":"ref10"},{"journal-title":"Deep Reinforcement Learning Workshop NeurIPS 2022","article-title":"Pink noise is all you need: Colored noise exploration in deep reinforcement learning","author":"Eberhard","key":"ref11"},{"key":"ref12","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","year":"2018"},{"article-title":"Maximum a posteriori policy optimisation","year":"2018","author":"Abdolmaleki","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcss.2007.08.009"},{"key":"ref15","article-title":"# exploration: A study of count-based exploration for deep reinforcement learning","volume":"30","author":"Tang","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref16","article-title":"Unifying count-based exploration and intrinsic motivation","volume":"29","author":"Bellemare","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref17","first-page":"2721","article-title":"Count-based exploration with neural density models","volume-title":"International conference on machine learning.","author":"Ostrovski","year":"2017"},{"key":"ref18","article-title":"Unifying count-based exploration and intrinsic motivation","volume":"29","author":"Bellemare","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref19","first-page":"2721","article-title":"Count-based exploration with neural density models","volume-title":"International conference on machine learning.","author":"Ostrovski","year":"2017"},{"key":"ref20","article-title":"# exploration: A study of count-based exploration for deep reinforcement learning","volume":"30","author":"Tang","year":"2017","journal-title":"Advances in neural information processing systems"},{"article-title":"Exploration by random network distillation","year":"2018","author":"Burda","key":"ref21"},{"article-title":"Exploration and anti-exploration with distributional random network distillation","year":"2024","author":"Yang","key":"ref22"},{"key":"ref23","first-page":"3040","article-title":"Social influence as intrinsic motivation for multi-agent deep reinforcement learning","volume-title":"International conference on machine learning.","author":"Jaques","year":"2019"},{"article-title":"Influence-based multi-agent exploration","volume-title":"International Conference on Learning Representations","author":"Wang","key":"ref24"},{"key":"ref25","first-page":"12 979","article-title":"Pmic: Improving multi-agent reinforcement learning with progressive mutual information collaboration","volume-title":"International Conference on Machine Learning","author":"Li"},{"key":"ref26","article-title":"Exploration with unreliable intrinsic reward in multi-agent reinforcement learning","author":"B\u00f6hmer","year":"2019","journal-title":"ICML em Exploration in Reinforcement Learning workshop"},{"key":"ref27","article-title":"Liir: Learning individual intrinsic reward in multi-agent reinforcement learning","volume":"32","author":"Du","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Ensemble value functions for efficient exploration in multi-agent reinforcement learning","year":"2023","author":"Sch\u00e4fer","key":"ref28"},{"key":"ref29","first-page":"6826","article-title":"Cooperative exploration for multi-agent deep reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Liu"},{"key":"ref30","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"article-title":"Value-decomposition networks for cooperative multi-agent learning","year":"2017","author":"Sunehag","key":"ref32"},{"issue":"1","key":"ref33","first-page":"7234","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"ref34","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume-title":"International conference on machine learning.","author":"Iqbal","year":"2019"},{"key":"ref35","article-title":"Deep multi-agent reinforcement learning for decentralized continuous cooperative control","volume":"19","author":"de Witt","year":"2020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3182\/20110828-6-IT-1002.01404"},{"article-title":"Benchmarking multi-agent deep reinforcement learning algorithms in cooperative tasks","year":"2020","author":"Papoudakis","key":"ref37"},{"article-title":"The starcraft multi-agent challenge","year":"2019","author":"Samvelyan","key":"ref38"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2024,6,30]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10649966.pdf?arnumber=10649966","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T04:53:03Z","timestamp":1725943983000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10649966\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10649966","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}