{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T02:56:48Z","timestamp":1776740208317,"version":"3.51.2"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T00:00:00Z","timestamp":1692576000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T00:00:00Z","timestamp":1692576000000},"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":[[2023,8,21]]},"DOI":"10.1109\/cog57401.2023.10333220","type":"proceedings-article","created":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T13:48:21Z","timestamp":1701697701000},"page":"1-8","source":"Crossref","is-referenced-by-count":11,"title":["Mastering Strategy Card Game (Hearthstone) with Improved Techniques"],"prefix":"10.1109","author":[{"given":"Changnan","family":"Xiao","sequence":"first","affiliation":[{"name":"ByteDance"}]},{"given":"Yongxin","family":"Zhang","sequence":"additional","affiliation":[{"name":"ByteDance"}]},{"given":"Xuefeng","family":"Huang","sequence":"additional","affiliation":[{"name":"ByteDance"}]},{"given":"Qinhan","family":"Huang","sequence":"additional","affiliation":[{"name":"ByteDance"}]},{"given":"Jie","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance"}]},{"given":"c","family":"Sun","sequence":"additional","affiliation":[{"name":"ByteDance"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Mastering strategy card game (legends of code and magic) via end-to-end policy and optimistic smooth fictitious play","author":"Xi","year":"2023"},{"key":"ref2","first-page":"507","article-title":"Agent57: Outperforming the atari human benchmark","volume-title":"International conference on machine learning","author":"Badia"},{"key":"ref3","article-title":"Unsupervised predictive memory in a goal-directed agent","author":"Wayne","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref5","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref7","article-title":"Suphx: Mastering mahjong with deep reinforcement learning","author":"Li","year":"2020"},{"key":"ref8","article-title":"Recurrent experience replay in distributed reinforcement learning","volume-title":"International conference on learning representations","author":"Kapturowski"},{"key":"ref9","first-page":"7487","article-title":"Stabilizing transformers for reinforcement learning","volume-title":"International conference on machine learning","author":"Parisotto"},{"key":"ref10","first-page":"2555","article-title":"Learning latent dynamics for planning from pixels","volume-title":"International conference on machine learning","author":"Hafner"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref12","article-title":"Regret minimization in games with incomplete information","volume":"20","author":"Zinkevich","year":"2007","journal-title":"Advances in neural information processing systems"},{"key":"ref13","first-page":"793","article-title":"Deep counterfactual regret minimization","volume-title":"International conference on machine learning","author":"Brown"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-018-1254-8"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-007-0149-x"},{"key":"ref16","first-page":"805","article-title":"Fictitious self-play in extensive-form games","volume-title":"International conference on machine learning","author":"Heinrich"},{"key":"ref17","first-page":"14293","article-title":"Last-iterate convergence in extensive-form games","volume":"34","author":"Lee","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","article-title":"Last-iterate convergence with full-and noisy-information feedback in two-player zero-sum games","author":"Abe","year":"2022"},{"key":"ref19","article-title":"A unified approach to reinforcement learning, quantal response equilibria, and two-player zero-sum games","author":"Sokota","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2017.8080446"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2017.8080452"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.29007\/mn6n"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.105032"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2018.8490368"},{"key":"ref25","first-page":"1","article-title":"Introducing the Hearthstone-AI Competition","author":"Dockhorn","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI50451.2021.9659984"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2012.2186810"},{"key":"ref28","first-page":"611","article-title":"Reinforcement learning in collectible card games: Preliminary results on legends of code and magic","volume-title":"Proceedings of the 18th Brazilian Symposium on Computer Games and Digital Entertainment","author":"Vieira"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/S0014-2921(98)00011-7"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.geb.2005.08.005"},{"key":"ref31","article-title":"Deep reinforcement learning from self-play in imperfect-information games","author":"Heinrich","year":"2016"},{"key":"ref32","first-page":"1407","article-title":"Impala: Scalable distributed deep-rl with importance weighted actor-learner architectures","volume-title":"International conference on machine learning","author":"Espeholt"},{"key":"ref33","article-title":"Tleague: A framework for competitive self-play based distributed multi-agent reinforcement learning","author":"Sun","year":"2020"},{"key":"ref34","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CoG57401.2023.10333220"}],"event":{"name":"2023 IEEE Conference on Games (CoG)","location":"Boston, MA, USA","start":{"date-parts":[[2023,8,21]]},"end":{"date-parts":[[2023,8,24]]}},"container-title":["2023 IEEE Conference on Games (CoG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10333091\/10333129\/10333220.pdf?arnumber=10333220","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T20:15:51Z","timestamp":1705004151000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10333220\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,21]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/cog57401.2023.10333220","relation":{},"subject":[],"published":{"date-parts":[[2023,8,21]]}}}