图 书 馆
强调时间差异学习的收敛性研究On Convergence of Emphatic Temporal-Difference Learning |
|
| 课程网址: | https://videolectures.net/videos/colt2015_yu_difference_learning |
| 主讲教师: | Huizhen Yu |
| 开课单位: | 信息不详。欢迎您在右侧留言补充。 |
| 开课时间: | 2025-02-04 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | We consider emphatic temporal-difference learning algorithms for policy evaluation in discounted Markov decision processes with finite spaces. Such algorithms were recently proposed by Sutton, Mahmood, and White as an improved solution to the problem of divergence of off-policy temporal-difference learning with linear function approximation. We present in this paper the first convergence proofs for two emphatic algorithms, ETD($\lambda$) and ELSTD($\lambda$). We prove, under general off-policy conditions, the convergence in $L^1$ for ELSTD($\lambda$) iterates and the almost sure convergence of the approximate value functions calculated by both algorithms. Our analysis involves new techniques with applications beyond emphatic algorithms leading, for example, to the first proof that standard TD($\lambda$) also converges under off-policy training for $\lambda$ sufficiently large. |
| 关 键 词: | 时间差学习算法; 线性函数; 散度问题 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2025-03-28：zsp |
| 最后编审: | 2025-03-28：zsp |
| 阅读次数: | 6 |