{"title":"多环境下爬行行为学习策略融合","authors":"Akihiko Yamaguchi, J. Takamatsu, T. Ogasawara","doi":"10.1109/ROBIO.2013.6739526","DOIUrl":null,"url":null,"abstract":"Though a reinforcement learning method is considered as a promising method for learning a robot's behavior from reward signals and adapting it for unknown environment, a standard reinforcement learning method is for a single environment. In this paper, to make a robot working in wider environments, we develop a reinforcement learning method for (1) estimating the current environment, (2) choosing a suitable policy for a known environment, and (3) making learning efficient when learning in a new environment by using transfer learning. To achieve them, we extend the learning strategy (LS) fusion method [1]. LS fusion is a method to learn multiple policies for a single task by applying multiple learning strategies (LSs) step by step. The key idea of environment estimation is using reward statistics of learned policies. For efficient learning, we design a learning strategy to transfer a policy learned in a different environment to one for the current environment. To verify the proposed method, we conducted some experiments where a small size humanoid robot learned a crawling task in several kinds of environments.","PeriodicalId":434960,"journal":{"name":"2013 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Learning strategy fusion for acquiring crawling behavior in multiple environments\",\"authors\":\"Akihiko Yamaguchi, J. Takamatsu, T. Ogasawara\",\"doi\":\"10.1109/ROBIO.2013.6739526\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Though a reinforcement learning method is considered as a promising method for learning a robot's behavior from reward signals and adapting it for unknown environment, a standard reinforcement learning method is for a single environment. In this paper, to make a robot working in wider environments, we develop a reinforcement learning method for (1) estimating the current environment, (2) choosing a suitable policy for a known environment, and (3) making learning efficient when learning in a new environment by using transfer learning. To achieve them, we extend the learning strategy (LS) fusion method [1]. LS fusion is a method to learn multiple policies for a single task by applying multiple learning strategies (LSs) step by step. The key idea of environment estimation is using reward statistics of learned policies. For efficient learning, we design a learning strategy to transfer a policy learned in a different environment to one for the current environment. To verify the proposed method, we conducted some experiments where a small size humanoid robot learned a crawling task in several kinds of environments.\",\"PeriodicalId\":434960,\"journal\":{\"name\":\"2013 IEEE International Conference on Robotics and Biomimetics (ROBIO)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2013-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2013 IEEE International Conference on Robotics and Biomimetics (ROBIO)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ROBIO.2013.6739526\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 IEEE International Conference on Robotics and Biomimetics (ROBIO)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ROBIO.2013.6739526","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Learning strategy fusion for acquiring crawling behavior in multiple environments
Though a reinforcement learning method is considered as a promising method for learning a robot's behavior from reward signals and adapting it for unknown environment, a standard reinforcement learning method is for a single environment. In this paper, to make a robot working in wider environments, we develop a reinforcement learning method for (1) estimating the current environment, (2) choosing a suitable policy for a known environment, and (3) making learning efficient when learning in a new environment by using transfer learning. To achieve them, we extend the learning strategy (LS) fusion method [1]. LS fusion is a method to learn multiple policies for a single task by applying multiple learning strategies (LSs) step by step. The key idea of environment estimation is using reward statistics of learned policies. For efficient learning, we design a learning strategy to transfer a policy learned in a different environment to one for the current environment. To verify the proposed method, we conducted some experiments where a small size humanoid robot learned a crawling task in several kinds of environments.