Finite Sample Analysis of LSTD with Random Projections and Eligibility Traces | |
Li HF(李海芳)1; Yingce Xia2; Wensheng Zhang1 | |
2018-04 | |
会议日期 | July 13-19 2018 |
会议地点 | Stockholm, Sweden |
英文摘要 | Policy evaluation with linear function approximation is an important problem in reinforcement learning. When facing high-dimensional feature spaces, such a problem becomes extremely hard considering the computation efficiency and quality of approximations. We propose a new algorithm, LSTD(λ)-RP, which leverages random projection techniques and takes eligibility traces into consideration to tackle the above two challenges. We carry out theoretical analysis of LSTD(λ)-RP, and provide meaningful upper bounds of the estimation error, approximation error and total generalization error. These results demonstrate that LSTD(λ)-RP can benefit from random projection and eligibility traces strategies, and LSTD(λ)-RP can achieve better performances than prior LSTDRP and LSTD(λ) algorithms. |
会议录出版者 | Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18) |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/26084] |
专题 | 精密感知与控制研究中心_人工智能与机器学习 |
通讯作者 | Li HF(李海芳) |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.University of Science and Technology of China |
推荐引用方式 GB/T 7714 | Li HF,Yingce Xia,Wensheng Zhang. Finite Sample Analysis of LSTD with Random Projections and Eligibility Traces[C]. 见:. Stockholm, Sweden. July 13-19 2018. |
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