{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:06:19Z","timestamp":1740099979737,"version":"3.37.3"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"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":[[2021,5]]},"DOI":"10.1109\/iscas51556.2021.9401286","type":"proceedings-article","created":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T21:33:36Z","timestamp":1619559216000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Combined Reinforcement Learning via Artificial Potential Field: A Case Study in Pommerman"],"prefix":"10.1109","author":[{"given":"Yuqi","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengze","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jieyuan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinhai","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1609\/aiide.v15i1.5220","article-title":"On Hard Exploration for Reinforcement Learning","volume":"15","author":"gao","year":"2019","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment"},{"article-title":"Skynet: A Top Deep RL Agent in the Inaugural Pommerman Team Competition","year":"2019","author":"gao","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1985.1087247"},{"key":"ref13","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref14","first-page":"5279","article-title":"Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation","author":"wu","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref15","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"year":"0","key":"ref16"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1609\/aiide.v15i1.5222","article-title":"Terminal prediction as an auxiliary task for deep reinforcement learning","author":"kartal","year":"2019","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"article-title":"Playing atari with deep reinforcement learning","year":"2013","author":"mnih","key":"ref3"},{"article-title":"Pommerman: A multi-agent playground","year":"2018","author":"resnick","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"article-title":"Deep Multi-Agent Reinforcement Learning with Relevance Graphs","year":"2018","author":"malysheva","key":"ref8"},{"journal-title":"Wikipedia the Free Encyclopedia","article-title":"Bomberman","year":"2020","key":"ref7"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"article-title":"Accelerating Training in Pommerman with Imitation and Reinforcement Learning","year":"2019","author":"meisheri","key":"ref9"}],"event":{"name":"2021 IEEE International Symposium on Circuits and Systems (ISCAS)","start":{"date-parts":[[2021,5,22]]},"location":"Daegu, Korea","end":{"date-parts":[[2021,5,28]]}},"container-title":["2021 IEEE International Symposium on Circuits and Systems (ISCAS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9401028\/9401051\/09401286.pdf?arnumber=9401286","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,25]],"date-time":"2022-12-25T16:16:24Z","timestamp":1671984984000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9401286\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/iscas51556.2021.9401286","relation":{},"subject":[],"published":{"date-parts":[[2021,5]]}}}