Knowledge Commons of Institute of Automation,CAS
ACDER: Augmented Curiosity-Driven Experience Replay | |
Li, Boyao1,2; Lu, Tao2; Li, Jiayi1,2; Lu, Ning1,2; Cai, Yinghao2; Wang, Shuo1,2 | |
2020-08 | |
会议名称 | IEEE International Conference on Robotics and Automation |
会议日期 | 2020.05.31-2020.08.31 |
会议地点 | Paris, France |
摘要 | Exploration in environments with sparse feedback remains a challenging research problem in reinforcement learning (RL). When the RL agent explores the environment randomly, it results in low exploration efficiency, especially in robotic manipulation tasks with high dimensional continuous state and action space. In this paper, we propose a novel method, called Augmented Curiosity-Driven Experience Replay (ACDER), which leverages (i) a new goal-oriented curiositydriven exploration to encourage the agent to pursue novel and task-relevant states more purposefully and (ii) the dynamic initial states selection as an automatic exploratory curriculum to further improve the sample-efficiency. Our approach complements Hindsight Experience Replay (HER) by introducing a new way to pursue valuable states. Experiments conducted on four challenging robotic manipulation tasks with binary rewards, including Reach, Push, Pick&Place and Multi-step Push. The empirical results show that our proposed method significantly outperforms existing methods in the first three basic tasks and also achieves satisfactory performance in multistep robotic task learning. |
收录类别 | EI |
语种 | 英语 |
七大方向——子方向分类 | 智能机器人 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/40236 |
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.中国科学院大学 2.中国科学院自动化研究所 |
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, Boyao,Lu, Tao,Li, Jiayi,et al. ACDER: Augmented Curiosity-Driven Experience Replay[C],2020. |
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 | ||
ACDER.pdf(3303KB) | 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