Knowledge Commons of Institute of Automation,CAS
DIMSAN: Fast Exploration with the Synergy between Density-based Intrinsic Motivation and Self-adaptive Action Noise | |
Li, Jiayi1,2; Li, Boyao3; Lu, Tao2; Lu, Ning1,2; Cai, Yinghao2; Wang, Shuo1,2,4 | |
2021-10 | |
会议名称 | 2021 IEEE International Conference on Robotics and Automation |
会议日期 | 2021.5.30-2021.6.5 |
会议地点 | 西安 |
会议举办国 | 中国 |
摘要 | Exploration in environments with sparse rewards remains a challenging problem in Deep Reinforcement Learning (DRL). For the off-policy method, it usually needs a large number of training samples. With the growing dimensions of state and action space, this method becomes more and more sample-inefficient. In this paper, we propose a novel fast exploration method for off-policy reinforcement learning, called Density-based Intrinsic Motivation and Self-adaptive Action Noise (DIMSAN). Our main contribution is twofold: (1) We propose a Density-based Intrinsic Motivation (DIM) method. It introduces a new intrinsic-reward generation mechanism based on samples' density estimation during experience replay and encourages the agent to seek novel and unfamiliar states. (2) We propose a Self-adaptive Action Noise (SAN) to deal with the exploration-exploitation tradeoffs, which could automatically change the exploration step through adding adaptive action space noise. The synergy between DIM and SAN could guide the agent to search the state and action space with high efficiency. We evaluate our method on the benchmark manipulation tasks and the designed challenging ones. Empirical results show that our method outperforms the existing methods in terms of convergence speed and sample efficiency, especially in challenging tasks. |
收录类别 | EI |
语种 | 英语 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48540 |
专题 | 多模态人工智能系统全国重点实验室_智能机器人系统研究 |
通讯作者 | Lu, Tao |
作者单位 | 1.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China 2.State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China 3.Research and Development Department, China Academy of Launch Vehicle Technology, Beijing, China 4.Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Shanghai, China. |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Li, Jiayi,Li, Boyao,Lu, Tao,et al. DIMSAN: Fast Exploration with the Synergy between Density-based Intrinsic Motivation and Self-adaptive Action Noise[C],2021. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
ICRA21_1292_FI.pdf(5599KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论