{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:19:58Z","timestamp":1766067598967,"version":"3.37.3"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020AAA0103401"],"award-info":[{"award-number":["2020AAA0103401"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9892077","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:56:04Z","timestamp":1664567764000},"page":"1-8","source":"Crossref","is-referenced-by-count":11,"title":["L2E: Learning to Exploit Your Opponent"],"prefix":"10.1109","author":[{"given":"Zhe","family":"Wu","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hang","family":"Xu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Zang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"An","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junliang","family":"Xing","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1126\/science.1259433","article-title":"Heads-up limit hold'em poker is solved","volume":"347","author":"bowling","year":"2015","journal-title":"Science"},{"key":"ref38","first-page":"550","article-title":"Bayes' bluff: opponent modelling in poker","author":"southey","year":"2005","journal-title":"Uncer-tainty in Artificial Intelligence"},{"key":"ref33","article-title":"Population based training of neural networks","author":"jaderberg","year":"0","journal-title":"ar Xiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.29007\/zh3q"},{"key":"ref31","article-title":"Diversity is all you need: Learning skills without a reward function","author":"eysenbach","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref30","article-title":"Noisy networks for exploration","author":"fortunato","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref37","first-page":"513","article-title":"A kernel method for the two-sample-problem","author":"gretton","year":"2007","journal-title":"Advances in neural information processing systems"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"1095","DOI":"10.1073\/pnas.39.10.1095","article-title":"Stochastic games","volume":"39","author":"shapley","year":"0","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"ref35","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":"2019","journal-title":"Nature"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"859","DOI":"10.1126\/science.aau6249","article-title":"Human-level performance in 3d multiplayer games with population-based reinforcement learning","volume":"364","author":"jaderberg","year":"2019","journal-title":"Science"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1329125.1329145"},{"key":"ref11","first-page":"1804","article-title":"Opponent modeling in deep reinforcement learning","author":"he","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref40","article-title":"Rlcard: A toolkit for reinforcement learning in card games","author":"zha","year":"0","journal-title":"ar Xiv preprint"},{"key":"ref12","first-page":"122","article-title":"Learning with opponent-learning awareness","author":"foerster","year":"0","journal-title":"International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref13","article-title":"Probabilistic recur-sive reasoning for multi-agent reinforcement learning","author":"wen","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref14","first-page":"374","article-title":"Iterative solution of games by fictitious play","volume":"13","author":"brown","year":"1951","journal-title":"Activity Analysis of Production and Allocation"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2015.2491611"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2009.5286483"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2011.6032018"},{"key":"ref18","first-page":"547","article-title":"Reasoning about hypothetical agent behaviours and their parameters","author":"albrecht","year":"0","journal-title":"International Conference on Au-tonomous Agents and Multiagent Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9665"},{"key":"ref28","article-title":"Wasserstein robust reinforcement learning","author":"abdullah","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref4","first-page":"73","article-title":"Identifying terrorist activity with ai plan recognition technology","volume":"26","author":"jarvis","year":"2005","journal-title":"AI Magazine"},{"key":"ref27","article-title":"Continuous adaptation via meta-learning in nonstationary and competitive environments","author":"ai-shedivat","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45108-0_9"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-007-0020-8"},{"key":"ref29","article-title":"Parameter space noise for exploration","author":"plappert","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref5","first-page":"817","article-title":"Learning against opponents with bounded memory","author":"powers","year":"0","journal-title":"International Joint Conference on Artificial Intelligence"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1111\/j.1468-0262.2005.00585.x"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/S0899-8256(03)00121-0"},{"key":"ref2","article-title":"Attention, intentions, and the structure of discourse","author":"grosz","year":"0","journal-title":"Computational Linguistics 1986"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2018.01.002"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-005-6825-4"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-015-9317-1"},{"key":"ref45","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref22","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref21","article-title":"Meta-learning in neural networks: A survey","author":"hospedales","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref24","article-title":"Learning to reinforcement learn","author":"wang","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref42","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref23","article-title":"On first-order meta-learning algorithms","author":"nichol","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref41","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref26","first-page":"4218","article-title":"Machine theory of mind","author":"rabinowitz","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref44","article-title":"Deep reinforcement learning from self-play in imperfect-information games","author":"heinrich","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref25","first-page":"2396","article-title":"Meta-gradient reinforcement learning","author":"xu","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref43","first-page":"1729","article-title":"Regret minimization in games with incomplete information","author":"zinkevich","year":"2008","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2022,7,18]]},"location":"Padua, Italy","end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09892077.pdf?arnumber=9892077","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T22:58:23Z","timestamp":1667516303000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9892077\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9892077","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}