A Rank-Based Sampling Framework For Offline Reinforcement Learning
2021 IEEE International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology (CEI)(2021)
摘要
Offline reinforcement learning (RL) is an attractive method that learns a policy purely from a previously collected dataset without additional interaction. However, it suffers the data quality issue that the performance of the policy is largely dependent on the previously collected dataset. In this paper, we propose a novel and robust sampling technique, Rank-Based sampling (RBS) to address this i...
更多查看译文
关键词
Offline Reinforcement Learning,Rank-Based,Non-Uniform Sampling
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要