{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:37:40Z","timestamp":1730230660768,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747378","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"4098-4102","source":"Crossref","is-referenced-by-count":1,"title":["Competitive Multi-Agent Reinforcement Learning with Self-Supervised Representation"],"prefix":"10.1109","author":[{"given":"DiJia","family":"Su","sequence":"first","affiliation":[{"name":"Princeton University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jason D.","family":"Lee","sequence":"additional","affiliation":[{"name":"Princeton University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John M.","family":"Mulvey","sequence":"additional","affiliation":[{"name":"Princeton University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"H. Vincent","family":"Poor","sequence":"additional","affiliation":[{"name":"Princeton University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Representation learning with contrastive predictive coding","author":"oord","year":"2018","journal-title":"arXiv preprint arXiv 1807 03748"},{"key":"ref11","first-page":"2","article-title":"The dynamics of reinforcement learning in cooperative multiagent systems","volume":"1998","author":"claus","year":"1998","journal-title":"Proceedings of AAAI\/IAAI"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref13","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","author":"sunehag","year":"2018","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref14","first-page":"122","article-title":"Learning with opponent-learning awareness","author":"foerster","year":"2018","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref15","article-title":"Learning against non-stationary agents with opponent modelling and deep reinforcement learning","author":"everett","year":"2018","journal-title":"Proceedings of the AAAI Spring Symposia"},{"key":"ref16","first-page":"4257","article-title":"Modeling others using oneself in multi-agent reinforcement learning","author":"raileanu","year":"2018","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref17","first-page":"4218","article-title":"Machine theory of mind","author":"rabinowitz","year":"2018","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref18","first-page":"1804","article-title":"Opponent modeling in deep reinforcement learning","author":"he","year":"2016","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref19","first-page":"1802","article-title":"Learning policy representations in multiagent systems","author":"grover","year":"2018","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01228-7"},{"key":"ref4","article-title":"Musbo: Model-based uncertainty regularized and sample efficient batch optimization for deployment constrained reinforcement learning","author":"su","year":"2021","journal-title":"arXiv preprint arXiv 2102 12041"},{"key":"ref27","first-page":"5279","article-title":"Scalable trust-region method for deep reinforcement learning using kronecker-factored approximation","volume":"30","author":"wu","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref6","article-title":"Model based reinforcement learning for atari","author":"kaiser","year":"2019","journal-title":"Proceedings of the International Conference on Learning Representations"},{"article-title":"Aiden – reinforcement learning for order execution","year":"0","author":"burhani","key":"ref5"},{"key":"ref8","first-page":"2536","article-title":"Context encoders: Feature learning by inpainting","author":"pathak","year":"2016","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref7","article-title":"Sample efficient actor-critic with experience replay","author":"wang","year":"2016","journal-title":"arXiv preprint arXiv 1611 01224"},{"key":"ref2","first-page":"9187","article-title":"Conqur: Mitigating delusional bias in deep q-learning","author":"su","year":"2020","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref9","article-title":"Reinforcement learning with unsupervised auxiliary tasks","author":"jaderberg","year":"2016","journal-title":"arXiv preprint arXiv 1611 05397"},{"key":"ref1","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":"ref20","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"},{"key":"ref22","article-title":"Dealing with non-stationarity in multi-agent deep reinforcement learning","author":"papoudakis","year":"2019","journal-title":"arXiv preprint arXiv 1906 04329"},{"key":"ref21","article-title":"Predicting what you already know helps: Provable self-supervised learning","author":"lee","year":"2020","journal-title":"arXiv preprint arXiv 2008 06439"},{"key":"ref24","article-title":"Reinforcement learning with augmented data","volume":"33","author":"laskin","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref23","first-page":"1407","article-title":"Impala: Scalable distributed deep-rl with importance weighted actor-learner architectures","author":"espeholt","year":"2018","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref26","article-title":"The surprising effectiveness of mappo in cooperative, multi-agent games","author":"yu","year":"2021","journal-title":"arXiv preprint arXiv 2103 05767"},{"key":"ref25","article-title":"Pettingzoo: Gym for multi-agent reinforcement learning","volume":"34","author":"terry","year":"2021","journal-title":"Advances in neural information processing systems"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747378.pdf?arnumber=9747378","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:10:46Z","timestamp":1661199046000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747378\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747378","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}