图 书 馆
海报聚焦：基于结构知识的强化学习中的情境依赖空间抽象Poster Spotlights: Situation Dependent Spatial Abstraction in Reinforcement Learning Based on Structural Knowledge |
|
| 课程网址: | http://videolectures.net/icml09_frommberger_sdsarlbsk/ |
| 主讲教师: | Lutz Frommberger |
| 开课单位: | 不来梅大学 |
| 开课时间: | 2009-08-26 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | State space abstraction reduces the size of a representation by factoring out details that are not relevant for solving a task at hand. But even in abstract representations not every detail is relevant in any situation. In cases where the structure of the environment only allows for one particular action selection, all information that does not relate to the structure can be omitted. We present a method to identify such cases in a reinforcement learning setting and abstract from non-structural details when appropriate to shrink the state space and allow for knowledge reuse. A significant performance improvement of this approach is demonstrated in a goal-directed robot navigation task. |
| 关 键 词: | 状态空间; 强化学习; 机器人 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2019-04-23：lxf |
| 阅读次数: | 32 |