{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T06:54:29Z","timestamp":1762066469785,"version":"build-2065373602"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,8,21]]},"DOI":"10.1109\/cog51982.2022.9893651","type":"proceedings-article","created":{"date-parts":[[2022,9,20]],"date-time":"2022-09-20T19:33:31Z","timestamp":1663702411000},"page":"261-267","source":"Crossref","is-referenced-by-count":2,"title":["Reinforcement Learning using Reward Expectations in Scenarios with Aleatoric Uncertainties"],"prefix":"10.1109","author":[{"given":"Yubin","family":"Wang","sequence":"first","affiliation":[{"name":"PLA SSF Information Engineering University,Zhengzhou,China"}]},{"given":"Yifeng","family":"Sun","sequence":"additional","affiliation":[{"name":"PLA SSF Information Engineering University,Zhengzhou,China"}]},{"given":"Jiang","family":"Wu","sequence":"additional","affiliation":[{"name":"PLA SSF Information Engineering University,Zhengzhou,China"}]},{"given":"Hao","family":"Hu","sequence":"additional","affiliation":[{"name":"PLA SSF Information Engineering University,Zhengzhou,China"}]},{"given":"Zhiqiang","family":"Wu","sequence":"additional","affiliation":[{"name":"PLA SSF Information Engineering University,Zhengzhou,China"}]},{"given":"Weigui","family":"Huang","sequence":"additional","affiliation":[{"name":"PLA SSF Information Engineering University,Zhengzhou,China"}]}],"member":"263","reference":[{"article-title":"Estimating Risk and Uncertainty in Deep Reinforcement Learning","year":"2019","author":"clements","key":"ref10"},{"article-title":"Distributional Reinforcement Learning for Efficient Exploration","year":"2019","author":"mavrin","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-020-02034-2"},{"article-title":"Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization","year":"2021","author":"tang","key":"ref13"},{"year":"0","key":"ref14"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","article-title":"Grandmaster level in StarCraft II using multi-agent reinforcement learning","volume":"575","author":"vinyals","year":"7782","journal-title":"Nature"},{"article-title":"StarCraft II: A New Challenge for Reinforcement Learning","year":"2017","author":"vinyals","key":"ref16"},{"article-title":"Dota 2 with Large Scale Deep Reinforcement Learning","year":"2019","author":"berner","key":"ref17"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"silver","year":"7587","journal-title":"Nature"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s13218-020-00647-w"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.strusafe.2008.06.020"},{"article-title":"Exploration in Deep Reinforcement Learning: A Comprehensive Survey","year":"2021","author":"yang","key":"ref7"},{"article-title":"Deep Reinforcement Learning for Decentralized Multi-Robot Exploration with Macro Actions","year":"2021","author":"tan","key":"ref2"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/URAI.2018.8441797"},{"article-title":"Distributional Reinforcement Learning with Quantile Regression","year":"2017","author":"dabney","key":"ref9"}],"event":{"name":"2022 IEEE Conference on Games (CoG)","start":{"date-parts":[[2022,8,21]]},"location":"Beijing, China","end":{"date-parts":[[2022,8,24]]}},"container-title":["2022 IEEE Conference on Games (CoG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9893561\/9893544\/09893651.pdf?arnumber=9893651","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T23:41:53Z","timestamp":1670283713000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9893651\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/cog51982.2022.9893651","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}