{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T19:14:09Z","timestamp":1767986049067,"version":"3.49.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"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":[[2020,8]]},"DOI":"10.1109\/cog47356.2020.9231562","type":"proceedings-article","created":{"date-parts":[[2020,10,21]],"date-time":"2020-10-21T18:05:50Z","timestamp":1603303550000},"page":"184-191","source":"Crossref","is-referenced-by-count":3,"title":["Exploring Unknown States with Action Balance"],"prefix":"10.1109","author":[{"given":"Song","family":"Yan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Yingfeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hu","family":"Yujing","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fan","family":"Changjie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/509961.509965"},{"key":"ref11","article-title":"Unifying count-based exploration and intrinsic motivation","author":"bellemare","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref12","article-title":"Count-Based Exploration with Neural Density Models","author":"ostrovski","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/344"},{"key":"ref14","article-title":"Conditional image generation with pixelcnn decoders","author":"van den oord","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref15","article-title":"Episodic Curiosity through Reachability","author":"savinov","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref16","article-title":"Never Give Up: Learning Directed Exploration Strategies","author":"badia","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102459"},{"key":"ref18","article-title":"Benchmarking Bonus-Based Exploration Methods on the Arcade Learning Environment","author":"ta\u00a8?ga","year":"2019"},{"key":"ref19","article-title":"A survey on intrinsic motivation in reinforcement learning","author":"aubret","year":"2019","journal-title":"CoRR"},{"key":"ref4","article-title":"Exploration by random network distillation","author":"burda","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref3","first-page":"278","article-title":"Policy Invariance Under Reward Transformations: Theory and Application to Reward Shaping","author":"ng","year":"1999","journal-title":"Proceedings of the Sixteenth International Conference on Machine Learning"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref8","article-title":"Near-Optimal Reinforcement Learning in Polynomial Time","author":"kearns","year":"2002","journal-title":"Machine Learning"},{"key":"ref7","first-page":"953","article-title":"R-MAX - A General Polynomial Time Algorithm for Near-Optimal Reinforcement Learning","author":"brafman","year":"2001","journal-title":"Proceedings of the Seventeenth International Joint Conference on Artificial Intelligence"},{"key":"ref2","article-title":"Proximal Policy Optimization Algorithms","author":"schulman","year":"2017"},{"key":"ref9","first-page":"2753","article-title":"# exploration: A study of count-based exploration for deep reinforcement learning","author":"tang","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref20","article-title":"Bandit based monte-carlo planning","author":"kocsis","year":"2006","journal-title":"European Conference on Machine Learning"},{"key":"ref22","article-title":"Is Q-Learning Provably Efficient?","author":"jin","year":"2018","journal-title":"Neural Information Processing Systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref24","first-page":"1928","article-title":"Asynchronous Methods for Deep Reinforcement Learning","author":"mnih","year":"2016","journal-title":"Proceedings of the 33nd International Conference on Machine Learning"},{"key":"ref23","article-title":"Go-Explore: a New Approach for Hard-Exploration Problems","author":"ecoffet","year":"2019","journal-title":"CoRR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/434"},{"key":"ref25","article-title":"Provably Efficient Maximum Entropy Exploration","author":"hazan","year":"2019","journal-title":"Proceedings of the 36th International Conference on Machine Learning"}],"event":{"name":"2020 IEEE Conference on Games (CoG)","location":"Osaka, Japan","start":{"date-parts":[[2020,8,24]]},"end":{"date-parts":[[2020,8,27]]}},"container-title":["2020 IEEE Conference on Games (CoG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9222389\/9231525\/09231562.pdf?arnumber=9231562","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T15:45:26Z","timestamp":1656344726000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9231562\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/cog47356.2020.9231562","relation":{},"subject":[],"published":{"date-parts":[[2020,8]]}}}