Yutai Zhou, Shawn Manuel, Peter Morales, Sheng Li, Jaime Peña, R. Allen
{"title":"多智能体强化学习的分布式框架研究","authors":"Yutai Zhou, Shawn Manuel, Peter Morales, Sheng Li, Jaime Peña, R. Allen","doi":"10.1109/HPEC43674.2020.9286212","DOIUrl":null,"url":null,"abstract":"Some of the most important publications in deep reinforcement learning over the last few years have been fueled by access to massive amounts of computation through large scale distributed systems. The success of these approaches in achieving human-expert level performance on several complex video-game environments has motivated further exploration into the limits of these approaches as computation increases. In this paper, we present a distributed RL training framework designed for super computing infrastructures such as the MIT SuperCloud. We review a collection of challenging learning environments-such as Google Research Football, StarCraft II, and Multi-Agent Mujoco- which are at the frontier of reinforcement learning research. We provide results on these environments that illustrate the current state of the field on these problems. Finally, we also quantify and discuss the computational requirements needed for performing RL research by enumerating all experiments performed on these environments.","PeriodicalId":168544,"journal":{"name":"2020 IEEE High Performance Extreme Computing Conference (HPEC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Towards a Distributed Framework for Multi-Agent Reinforcement Learning Research\",\"authors\":\"Yutai Zhou, Shawn Manuel, Peter Morales, Sheng Li, Jaime Peña, R. Allen\",\"doi\":\"10.1109/HPEC43674.2020.9286212\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Some of the most important publications in deep reinforcement learning over the last few years have been fueled by access to massive amounts of computation through large scale distributed systems. The success of these approaches in achieving human-expert level performance on several complex video-game environments has motivated further exploration into the limits of these approaches as computation increases. In this paper, we present a distributed RL training framework designed for super computing infrastructures such as the MIT SuperCloud. We review a collection of challenging learning environments-such as Google Research Football, StarCraft II, and Multi-Agent Mujoco- which are at the frontier of reinforcement learning research. We provide results on these environments that illustrate the current state of the field on these problems. Finally, we also quantify and discuss the computational requirements needed for performing RL research by enumerating all experiments performed on these environments.\",\"PeriodicalId\":168544,\"journal\":{\"name\":\"2020 IEEE High Performance Extreme Computing Conference (HPEC)\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-09-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 IEEE High Performance Extreme Computing Conference (HPEC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/HPEC43674.2020.9286212\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 IEEE High Performance Extreme Computing Conference (HPEC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/HPEC43674.2020.9286212","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Towards a Distributed Framework for Multi-Agent Reinforcement Learning Research
Some of the most important publications in deep reinforcement learning over the last few years have been fueled by access to massive amounts of computation through large scale distributed systems. The success of these approaches in achieving human-expert level performance on several complex video-game environments has motivated further exploration into the limits of these approaches as computation increases. In this paper, we present a distributed RL training framework designed for super computing infrastructures such as the MIT SuperCloud. We review a collection of challenging learning environments-such as Google Research Football, StarCraft II, and Multi-Agent Mujoco- which are at the frontier of reinforcement learning research. We provide results on these environments that illustrate the current state of the field on these problems. Finally, we also quantify and discuss the computational requirements needed for performing RL research by enumerating all experiments performed on these environments.