{"title":"TGRL:一种教师引导的强化学习算法","authors":"Idan Shenfeld, Zhang-Wei Hong, Aviv Tamar, Pulkit Agrawal","doi":"10.48550/arXiv.2307.03186","DOIUrl":null,"url":null,"abstract":"Learning from rewards (i.e., reinforcement learning or RL) and learning to imitate a teacher (i.e., teacher-student learning) are two established approaches for solving sequential decision-making problems. To combine the benefits of these different forms of learning, it is common to train a policy to maximize a combination of reinforcement and teacher-student learning objectives. However, without a principled method to balance these objectives, prior work used heuristics and problem-specific hyperparameter searches to balance the two objectives. We present a $\\textit{principled}$ approach, along with an approximate implementation for $\\textit{dynamically}$ and $\\textit{automatically}$ balancing when to follow the teacher and when to use rewards. The main idea is to adjust the importance of teacher supervision by comparing the agent's performance to the counterfactual scenario of the agent learning without teacher supervision and only from rewards. If using teacher supervision improves performance, the importance of teacher supervision is increased and otherwise it is decreased. Our method, $\\textit{Teacher Guided Reinforcement Learning}$ (TGRL), outperforms strong baselines across diverse domains without hyper-parameter tuning.","PeriodicalId":74529,"journal":{"name":"Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning","volume":"41 1","pages":"31077-31093"},"PeriodicalIF":0.0000,"publicationDate":"2023-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"TGRL: An Algorithm for Teacher Guided Reinforcement Learning\",\"authors\":\"Idan Shenfeld, Zhang-Wei Hong, Aviv Tamar, Pulkit Agrawal\",\"doi\":\"10.48550/arXiv.2307.03186\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Learning from rewards (i.e., reinforcement learning or RL) and learning to imitate a teacher (i.e., teacher-student learning) are two established approaches for solving sequential decision-making problems. To combine the benefits of these different forms of learning, it is common to train a policy to maximize a combination of reinforcement and teacher-student learning objectives. However, without a principled method to balance these objectives, prior work used heuristics and problem-specific hyperparameter searches to balance the two objectives. We present a $\\\\textit{principled}$ approach, along with an approximate implementation for $\\\\textit{dynamically}$ and $\\\\textit{automatically}$ balancing when to follow the teacher and when to use rewards. The main idea is to adjust the importance of teacher supervision by comparing the agent's performance to the counterfactual scenario of the agent learning without teacher supervision and only from rewards. If using teacher supervision improves performance, the importance of teacher supervision is increased and otherwise it is decreased. Our method, $\\\\textit{Teacher Guided Reinforcement Learning}$ (TGRL), outperforms strong baselines across diverse domains without hyper-parameter tuning.\",\"PeriodicalId\":74529,\"journal\":{\"name\":\"Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning\",\"volume\":\"41 1\",\"pages\":\"31077-31093\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-07-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2307.03186\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2307.03186","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
TGRL: An Algorithm for Teacher Guided Reinforcement Learning
Learning from rewards (i.e., reinforcement learning or RL) and learning to imitate a teacher (i.e., teacher-student learning) are two established approaches for solving sequential decision-making problems. To combine the benefits of these different forms of learning, it is common to train a policy to maximize a combination of reinforcement and teacher-student learning objectives. However, without a principled method to balance these objectives, prior work used heuristics and problem-specific hyperparameter searches to balance the two objectives. We present a $\textit{principled}$ approach, along with an approximate implementation for $\textit{dynamically}$ and $\textit{automatically}$ balancing when to follow the teacher and when to use rewards. The main idea is to adjust the importance of teacher supervision by comparing the agent's performance to the counterfactual scenario of the agent learning without teacher supervision and only from rewards. If using teacher supervision improves performance, the importance of teacher supervision is increased and otherwise it is decreased. Our method, $\textit{Teacher Guided Reinforcement Learning}$ (TGRL), outperforms strong baselines across diverse domains without hyper-parameter tuning.