A model-based approach to solve the sparse reward problem
文献类型：会议论文
| 作者 | Li SL(李帅龙)1,2,3 ; Wang XH(王晓辉)1,2,3; Zhang W(张伟)1,2; Zhang X(张鑫)1,2
|
| 出版日期 | 2021 |
| 会议日期 | August 20-22, 2021 |
| 会议地点 | Virtual, Yibin, China |
| 关键词 | reinforcement learning model-based method the sparsity of reward |
| 页码 | 476-480 |
| 英文摘要 | For reinforcement learning (RL) algorithms, the sparsity of reward has always been a problem to be solved. Because reinforcement learning cannot get effective feedback in most cases, the agent is difficult to learn effectively. We propose a model-based algorithm to create extra rewards and increase reward density to make it easy to learning. To reshape rewards, we use model error as an extra reward and add it to the return. We test our approach in the Google Research Football Environment, and our algorithm gets good results. |
| 源文献作者 | Chongqing University ; et al. ; IEEE ; Sichuan University of Science and Engineering ; Tongji University ; University of Electronic Science and Technology of China |
| 产权排序 | 1 |
| 会议录 | 2021 4th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2021
 |
| 会议录出版者 | IEEE |
| 会议录出版地 | NEW YORK |
| 语种 | 英语 |
| ISBN号 | 978-1-6654-1322-0 |
| 源URL | [http://ir.sia.cn/handle/173321/29856]  |
| 专题 | 沈阳自动化研究所_空间自动化技术研究室 |
| 通讯作者 | Li SL(李帅龙) |
| 作者单位 | 1.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China 2.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110016, China 3.University of Chinese Academy of Sciences, Beijing 100049, China |
| 推荐引用方式 GB/T 7714 | Li SL,Wang XH,Zhang W,et al. A model-based approach to solve the sparse reward problem[C]. 见:. Virtual, Yibin, China. August 20-22, 2021. |
入库方式： OAI收割
来源：沈阳自动化研究所
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。