{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,25]],"date-time":"2026-01-25T03:21:24Z","timestamp":1769311284682,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":16,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,7,3]],"date-time":"2020-07-03T00:00:00Z","timestamp":1593734400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,7,3]]},"DOI":"10.1145\/3409501.3409517","type":"proceedings-article","created":{"date-parts":[[2020,8,25]],"date-time":"2020-08-25T14:56:37Z","timestamp":1598367397000},"page":"204-208","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Value Function Dynamic Estimation in Reinforcement Learning based on Data Adequacy"],"prefix":"10.1145","author":[{"given":"Huifan","family":"Gao","sequence":"first","affiliation":[{"name":"Xiamen Key Laboratory of Big Data Intelligent Analysis and Decision, Department of Automation, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinghui","family":"Pan","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Shenzhen University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Tang","sequence":"additional","affiliation":[{"name":"Newcastle Business School, Northumbria University, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifeng","family":"Zeng","sequence":"additional","affiliation":[{"name":"Department of Computer & Information Sciences, Northumbria University, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peihua","family":"Chai","sequence":"additional","affiliation":[{"name":"Xiamen Key Laboratory of Big Data Intelligent Analysis and Decision, Department of Automation, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Langcai","family":"Cao","sequence":"additional","affiliation":[{"name":"Xiamen Key Laboratory of Big Data Intelligent Analysis and Decision, Department of Automation, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,8,25]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Sutton R. and Barto A.. 1998. Reinforcement Learning:An Introduction.  Sutton R. and Barto A.. 1998. Reinforcement Learning:An Introduction.","DOI":"10.1109\/TNN.1998.712192"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Bellman R.. 1957. On a dynamic programming approach to the caterer problem-i. Management Science 3.  Bellman R.. 1957. On a dynamic programming approach to the caterer problem-i. Management Science 3.","DOI":"10.1287\/mnsc.3.3.270"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"e_1_3_2_1_4_1","unstructured":"Project Malmo. https:\/\/www.microsoft.com\/en-us\/research\/project\/project-malmo\/.  Project Malmo. https:\/\/www.microsoft.com\/en-us\/research\/project\/project-malmo\/."},{"key":"e_1_3_2_1_5_1","volume-title":"Proc. 15th International Conference on Machine Learning.","author":"Hu J.","unstructured":"Hu , J. and Wellman , M .. 1998. Multi-agent reinforcement learning: Theoretical framework andnan algorithms . In Proc. 15th International Conference on Machine Learning. Hu, J. and Wellman, M.. 1998. Multi-agent reinforcement learning: Theoretical framework andnan algorithms. In Proc. 15th International Conference on Machine Learning."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.5555\/3091574.3091594"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"e_1_3_2_1_9_1","volume-title":"HogRider: Champion Agent of Microsoft Malmo Collaborative AI Challenge. In Thirty-Second AAAI Conference on Artificial Intelligence.","author":"Xiong Y.","unstructured":"Xiong , Y. , Chen , H. , Zhao , M. , and An , B .. 2018 . HogRider: Champion Agent of Microsoft Malmo Collaborative AI Challenge. In Thirty-Second AAAI Conference on Artificial Intelligence. Xiong, Y., Chen, H., Zhao, M., and An, B.. 2018. HogRider: Champion Agent of Microsoft Malmo Collaborative AI Challenge. In Thirty-Second AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_2_1_10_1","unstructured":"Wang W. Hao J. Wang Y. and Taylor M.. 2018. Towards cooperation in sequential prisoner's dilemmas: a deep multiagent reinforcement learning approach.  Wang W. Hao J. Wang Y. and Taylor M.. 2018. Towards cooperation in sequential prisoner's dilemmas: a deep multiagent reinforcement learning approach."},{"key":"e_1_3_2_1_11_1","volume-title":"Seventeenth International Conference on Machine Learning.","author":"Strens M..","year":"2000","unstructured":"Strens , M.. 2000 . A Bayesian Framework for Reinforcement Learning . Seventeenth International Conference on Machine Learning. Strens, M.. 2000. A Bayesian Framework for Reinforcement Learning. Seventeenth International Conference on Machine Learning."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1002055"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2011.01.001"},{"key":"e_1_3_2_1_14_1","unstructured":"Chowdhury A. and Koval D.. Fundamentals of probability and statistics. Power Distribution System Reliability Practical Methods And Applications.  Chowdhury A. and Koval D.. Fundamentals of probability and statistics. Power Distribution System Reliability Practical Methods And Applications."},{"key":"e_1_3_2_1_15_1","unstructured":"Mojang. Minecraft. https:\/\/minecraft.net\/en-us\/.  Mojang. Minecraft. https:\/\/minecraft.net\/en-us\/."},{"key":"e_1_3_2_1_16_1","volume-title":"General Game Learning Using Knowledge Transfer. IJCAI 2007, Proceedings of the 20th International Joint Conference on Artificial Intelligence","author":"Banerjee B.","year":"2007","unstructured":"Banerjee , B. , and Stone , P .. 2007 . General Game Learning Using Knowledge Transfer. IJCAI 2007, Proceedings of the 20th International Joint Conference on Artificial Intelligence , Hyderabad, India , January 6-12, 2007 . Morgan Kaufmann Publishers Inc. Banerjee, B., and Stone, P.. 2007. General Game Learning Using Knowledge Transfer. IJCAI 2007, Proceedings of the 20th International Joint Conference on Artificial Intelligence, Hyderabad, India, January 6-12, 2007. Morgan Kaufmann Publishers Inc."}],"event":{"name":"HPCCT & BDAI 2020: 2020 4th High Performance Computing and Cluster Technologies Conference & 2020 3rd International Conference on Big Data and Artificial Intelligence","location":"Qingdao China","acronym":"HPCCT & BDAI 2020","sponsor":["Xi'an Jiaotong-Liverpool University Xi'an Jiaotong-Liverpool University"]},"container-title":["Proceedings of the 2020 4th High Performance Computing and Cluster Technologies Conference & 2020 3rd International Conference on Big Data and Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3409501.3409517","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3409501.3409517","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:38:40Z","timestamp":1750199920000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3409501.3409517"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7,3]]},"references-count":16,"alternative-id":["10.1145\/3409501.3409517","10.1145\/3409501"],"URL":"https:\/\/doi.org\/10.1145\/3409501.3409517","relation":{},"subject":[],"published":{"date-parts":[[2020,7,3]]},"assertion":[{"value":"2020-08-25","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}