图 书 馆
加固有限的强化学习：利用Bayes风险POMDPs主动学习Reinforcement Learning with Limited Reinforcement: Using Bayes Risk for Active Learning in POMDPs |
|
| 课程网址: | http://videolectures.net/icml08_doshi_rlw/ |
| 主讲教师: | Finale Doshi |
| 开课单位: | 剑桥大学 |
| 开课时间: | 2008-08-06 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | Partially Observable Markov Decision Processes (POMDPs) have succeeded in planning domains because they optimally trade between actions that increase an agent's knowledge and actions that increase an agent's reward. Unfortunately, most POMDPs are defined with a large number of parameters which are difficult to specify only from domain knowledge. In this paper, we treat the POMDP model parameters as additional hidden state in a "model-uncertainty" POMDP and develop an approximate algorithm for planning in the this larger POMDP. The approximation, coupled with model-directed queries, allows the planner to actively learn good policies. We demonstrate our approach on several standard POMDP problems. |
| 关 键 词: | 马尔可夫决策过程; 贝叶斯学习; POMDP模型; 动作选择与贝叶斯风险 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2020-06-03：张荧(课程编辑志愿者) |
| 阅读次数: | 110 |