图 书 馆
正规化政策评价与改进的线性互补Linear Complementarity for Regularized Policy Evaluation and Improvement |
|
| 课程网址: | http://videolectures.net/nips2010_johns_lcr/ |
| 主讲教师: | Jeff Johns |
| 开课单位: | 杜克大学 |
| 开课时间: | 2011-01-12 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | Recent work in reinforcement learning has emphasized the power of L1 regularization to perform feature selection and prevent overfitting. We propose formulating the L1 regularized linear fixed point problem as a linear complementarity problem (LCP). This formulation offers several advantages over the LARS-inspired formulation, LARS-TD. The LCP formulation allows the use of efficient off-the-shelf solvers, leads to a new uniqueness result, and can be initialized with starting points from similar problems (warm starts). We demonstrate that warm starts, as well as the efficiency of LCP solvers, can speed up policy iteration. Moreover, warm starts permit a form of modified policy iteration that can be used to approximate a "greedy" homotopy path, a generalization of the LARS-TD homotopy path that combines policy evaluation and optimization. |
| 关 键 词: | 强化学习; L1正则化; 线性互补问题 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2019-09-06：lxf |
| 阅读次数: | 37 |