{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T06:47:50Z","timestamp":1730270870695,"version":"3.28.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"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":[[2022,10,23]]},"DOI":"10.1109\/iros47612.2022.9981763","type":"proceedings-article","created":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:38:15Z","timestamp":1672083495000},"page":"12441-12447","source":"Crossref","is-referenced-by-count":0,"title":["Safe adaptation in multiagent competition"],"prefix":"10.1109","author":[{"given":"Macheng","family":"Shen","sequence":"first","affiliation":[{"name":"Massachusetts Institute of Technology,Department of Mechanical Engineering,Cambridge,MA,USA,02139"}]},{"given":"Jonathan P.","family":"How","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology,Department of Aeronautics and Astronautics,Cambridge,MA,USA,02139"}]}],"member":"263","reference":[{"key":"ref1","article-title":"RL2: Fast reinforcement learning via slow reinforcement learning","author":"Duan","year":"2016","journal-title":"arXiv preprint"},{"key":"ref2","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"International conference on machine learning PMLR","author":"Finn","year":"2017"},{"key":"ref3","article-title":"Deep online learning via meta-learning: Continual adaptation for model-based rl","volume-title":"International Conference on Learning Representations","author":"Nagabandi","year":"2018"},{"key":"ref4","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Nagabandi","year":"2018"},{"issue":"3","key":"ref5","first-page":"4","article-title":"Reptile: a scalable metalearning algorithm","volume":"2","author":"Nichol","year":"2018","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Continuous adaptation via meta-learning in nonstationary and competitive environments","volume-title":"International Conference on Learning Representations","author":"Al-Shedivat","year":"2018"},{"key":"ref7","article-title":"Learning with opponent-learning awareness","volume-title":"Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems","author":"Foerster","year":"2018"},{"key":"ref8","first-page":"5541","article-title":"A policy gradient algorithm for learning to learn in multiagent reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Kim","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.13673"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0308738101"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/2884.001.0001"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2716322"},{"volume-title":"Safe opponent-exploitation subgame refinement","year":"2022","author":"Liu","key":"ref13"},{"key":"ref14","article-title":"Safe and nested subgame solving for imperfect-information games","volume":"30","author":"Brown","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref16","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1126\/science.aau6249"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref20","article-title":"A unified game-theoretic approach to multiagent reinforcement learning","author":"Lanctot","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref21","article-title":"Emergent complexity via multi-agent competition","volume-title":"International Conference on Learning Representations","author":"Bansal","year":"2018"},{"key":"ref22","article-title":"Robust reinforcement learning using adversarial populations","author":"Vinitsky","year":"2020","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Real world games look like spinning tops","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Czarnecki","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.36.1.48"},{"key":"ref25","article-title":"Adversarial policies: Attacking deep reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Gleave","year":"2019"},{"key":"ref26","first-page":"1804","article-title":"Opponent modeling in deep reinforcement learning","volume-title":"International conference on machine learning","author":"He","year":"2016"},{"key":"ref27","first-page":"4257","article-title":"Modeling others using oneself in multi-agent reinforcement learning","volume-title":"International conference on machine learning","author":"Raileanu","year":"2018"},{"key":"ref28","first-page":"1802","article-title":"Learning policy representations in multiagent systems","volume-title":"International conference on machine learning","author":"Grover","year":"2018"},{"key":"ref29","article-title":"Variational autoencoders for opponent modeling in multi-agent systems","author":"Papoudakis","year":"2020","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014213"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6156"},{"key":"ref32","article-title":"Generalized proximal policy optimization with sample reuse","volume":"34","author":"Queeney","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/821"},{"key":"ref34","article-title":"Generative adversarial imitation learning","volume":"29","author":"Ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref35","article-title":"Facmac: Factored multi-agent centralised policy gradients","volume":"34","author":"Peng","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref36","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref37","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja","year":"2018"},{"key":"ref38","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"}],"event":{"name":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2022,10,23]]},"location":"Kyoto, Japan","end":{"date-parts":[[2022,10,27]]}},"container-title":["2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9981026\/9981028\/09981763.pdf?arnumber=9981763","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T05:09:54Z","timestamp":1706764194000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9981763\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,23]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/iros47612.2022.9981763","relation":{},"subject":[],"published":{"date-parts":[[2022,10,23]]}}}