{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:27:28Z","timestamp":1766068048948,"version":"3.28.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10611581","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"322-328","source":"Crossref","is-referenced-by-count":6,"title":["Stimulate the Potential of Robots via Competition"],"prefix":"10.1109","author":[{"given":"Kangyao","family":"Huang","sequence":"first","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology,Beijing,P. R. China,100084"}]},{"given":"Di","family":"Guo","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence,Beijing,China"}]},{"given":"Xinyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University,School of Vehicle and Mobility,Beijing,P. R. China,100084"}]},{"given":"Xiangyang","family":"Ji","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Automation,Beijing,P. R. China,100084"}]},{"given":"Huaping","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology,Beijing,P. R. China,100084"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2015.01282"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5878"},{"article-title":"Honor of Kings Arena: an Environment for Generalization in Competitive Reinforcement Learning","year":"2022","author":"Wei","key":"ref4"},{"key":"ref5","first-page":"26 318","article-title":"Exploration-Exploitation in Multi-Agent Competition: Convergence with Bounded Rationality","volume":"31","author":"Leonardos","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1108\/RIA-11-2022-0266"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1108\/RIA-10-2022-0258"},{"key":"ref9","first-page":"591","article-title":"Bio-inspired Multi-agent Model and\u0103Optimization Strategy for\u0103Collaborative Aerial Transport","volume-title":"Lecture Notes in Electrical Engineering","volume":"801","author":"Huang","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2021.100957"},{"article-title":"An Overview of Multi-Agent Reinforcement Learning from Game Theoretical Perspective","year":"2020","author":"Yang","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-09996-w"},{"key":"ref13","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"Lowe","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","year":"2021","author":"Yu","key":"ref14"},{"article-title":"Emergent complexity via multi-agent competition","volume-title":"6th International Conference on Learning Representations, ICLR 2018 - Conference Track Proceedings","author":"Bansal","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459761"},{"article-title":"The Emergence of Adversarial Communication in Multi-Agent Reinforcement Learning","year":"2020","author":"Blumenkamp","key":"ref17"},{"key":"ref18","first-page":"605","article-title":"Deterministic policy gradient algorithms","volume-title":"31st International Conference on Machine Learning, ICML 2014","volume":"1","author":"Silver"},{"article-title":"Continuous Control With Deep Re-inforcement Learning","volume-title":"4th International Conference on Learning Representations, ICLR 2016 - Conference Track Proceedings","author":"Erez","key":"ref19"},{"key":"ref20","first-page":"1889","article-title":"Trust Region Policy Optimization","volume-title":"32nd International Conference on Machine Learning, ICML 2015","volume":"3","author":"Abbeel"},{"article-title":"Proximal Policy Optimization Algorithms","year":"2017","author":"Schulman","key":"ref21"},{"key":"ref22","first-page":"2976","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"35th International Conference on Machine Learning, ICML 2018","volume":"5","author":"Haarnoja"},{"key":"ref23","first-page":"2587","article-title":"Addressing Function Approximation Error in Actor-Critic Methods","volume-title":"35th International Conference on Machine Learning, ICML 2018","volume":"4","author":"Fujimoto"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1108\/RIA-10-2022-0248"},{"key":"ref25","article-title":"RL Baselines3 Zoo","volume-title":"GitHub repository","author":"Raffin","year":"2020"},{"article-title":"openrlbenchmark","year":"2023","author":"Huang","key":"ref26"},{"key":"ref27","article-title":"Tianshou: A Highly Modularized Deep Reinforcement Learning Library","volume":"23","author":"Weng","year":"2022","journal-title":"Journal of Machine Learning Research"},{"key":"ref28","article-title":"ChainerRL: A deep reinforcement learning library","volume":"22","author":"Fujita","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"ref30","first-page":"1575","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"37th International Conference on Machine Learning, ICML 2020","author":"Chen"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765202"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080786"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561379"},{"article-title":"Negative Sampling for Contrastive Representation Learning: A Review","year":"2022","author":"Xu","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3031549"},{"article-title":"High-dimensional continuous control using generalized advantage estimation","volume-title":"4th International Conference on Learning Representations, ICLR 2016 - Conference Track Proceedings","author":"Schulman","key":"ref36"},{"article-title":"Policy Regularization via Noisy Advantage Values for Cooperative Multi-agent Actor-Critic methods","year":"2021","author":"Hu","key":"ref37"},{"article-title":"Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?","year":"2020","author":"de Witt","key":"ref38"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2024,5,13]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10611581.pdf?arnumber=10611581","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T04:19:16Z","timestamp":1723349956000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611581\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10611581","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}