Learning to Reweight Imaginary Transitions for Model-Based Reinforcement Learning | |
Huang, Wenzhen1,2; Yin Qiyue1,2; Zhang Junge1,2; Huang, Kaiqi1,2,3 | |
2021-02 | |
会议日期 | 2021-2 |
会议地点 | online |
英文摘要 | Model-based reinforcement learning (RL) is more sample efficient than model-free RL by using imaginary trajectories generated by the learned dynamics model. When the model is inaccurate or biased, imaginary trajectories may be deleterious for training the action-value and policy functions. To alleviate such problem, this paper proposes to adaptively |
会议录出版者 | AAAI Press |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/46602] |
专题 | 自动化研究所_智能感知与计算研究中心 |
作者单位 | 1.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China 2.CRISE, Institute of Automation, Chinese Academy of Sciences, Beijing, China 3.CAS Center for Excellence in Brain Science and Intelligence Technology, Beijing, China |
推荐引用方式 GB/T 7714 | Huang, Wenzhen,Yin Qiyue,Zhang Junge,et al. Learning to Reweight Imaginary Transitions for Model-Based Reinforcement Learning[C]. 见:. online. 2021-2. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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