A Novel Heterogeneous Actor-critic Algorithm with Recent Emphasizing Replay Memory
文献类型:期刊论文
作者 | Bao Xi2,3![]() ![]() ![]() ![]() |
刊名 | International Journal of Automation and Computing
![]() |
出版日期 | 2021 |
卷号 | 18期号:4页码:619-631 |
关键词 | Reinforcement learning (RL) actor-critic experience replay training efficiency manipulation skill learning |
ISSN号 | 1476-8186 |
DOI | 10.1007/s11633-021-1296-x |
英文摘要 | Reinforcement learning (RL) algorithms have been demonstrated to solve a variety of continuous control tasks. However, the training efficiency and performance of such methods limit further applications. In this paper, we propose an off-policy heterogeneous actor-critic (HAC) algorithm, which contains soft Q-function and ordinary Q-function. The soft Q-function encourages the exploration of a Gaussian policy, and the ordinary Q-function optimizes the mean of the Gaussian policy to improve the training efficiency. Experience replay memory is another vital component of off-policy RL methods. We propose a new sampling technique that emphasizes recently experienced transitions to boost the policy training. Besides, we integrate HAC with hindsight experience replay (HER) to deal with sparse reward tasks, which are common in the robotic manipulation domain. Finally, we evaluate our methods on a series of continuous control benchmark tasks and robotic manipulation tasks. The experimental results show that our method outperforms prior state-of-the-art methods in terms of training efficiency and performance, which validates the effectiveness of our method. |
源URL | [http://ir.ia.ac.cn/handle/173211/45068] ![]() |
专题 | 自动化研究所_学术期刊_International Journal of Automation and Computing |
作者单位 | 1.Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Shanghai 200031, China 2.University of Chinese Academy of Sciences, Beijing 100049, China 3.State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China |
推荐引用方式 GB/T 7714 | Bao Xi,Rui Wang,Shuo Wang,et al. A Novel Heterogeneous Actor-critic Algorithm with Recent Emphasizing Replay Memory[J]. International Journal of Automation and Computing,2021,18(4):619-631. |
APA | Bao Xi,Rui Wang,Shuo Wang,&Ying-Hao Cai.(2021).A Novel Heterogeneous Actor-critic Algorithm with Recent Emphasizing Replay Memory.International Journal of Automation and Computing,18(4),619-631. |
MLA | Bao Xi,et al."A Novel Heterogeneous Actor-critic Algorithm with Recent Emphasizing Replay Memory".International Journal of Automation and Computing 18.4(2021):619-631. |
入库方式: OAI收割
来源:自动化研究所
浏览0
下载0
收藏0
其他版本
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。