图 书 馆
主动强化学习Active Reinforcement Learning |
|
| 课程网址: | http://videolectures.net/icml08_epshteyn_arl/ |
| 主讲教师: | Arkady Epshteyn |
| 开课单位: | 谷歌公司 |
| 开课时间: | 2008-08-06 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | When the transition probabilities and rewards of a Markov Decision Process (MDP) are known, the agent can obtain the optimal policy without any interaction with the environment. However, exact transition probabilities are difficult for experts to specify. One option left to an agent is a long and potentially costly exploration of the environment. In this paper, we propose another alternative: given initial (possibly inaccurate) specification of the MDP, the agent determines the sensitivity of the optimal policy to changes in transitions and rewards. It then focuses its exploration on the regions of space to which the optimal policy is most sensitive. We show that the proposed exploration strategy performs well on several control and planning problems. |
| 关 键 词: | 马尔可夫决策; 转换概率; 代理商 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2019-04-18：cwx |
| 阅读次数: | 161 |