图 书 馆
未来信息最小化为PAC贝叶斯正则化的强化学习Future Information Minimization as PAC Bayes regularization in Reinforcement Learning |
|
| 课程网址: | http://videolectures.net/nipsworkshops2011_tishby_refinement/ |
| 主讲教师: | Naftali Tishby |
| 开课单位: | 希伯来大学 |
| 开课时间: | 2012-01-25 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | Interactions between an organism and its environment are commonly treated in the framework of Markov Decision Processes (MDP). While standard MDP is aimed at maximizing expected future rewards (value), the circular flow of information between the agent and its environment is generally ignored. In particular, the information gained from the environment by means of perception and the information involved in the process of action selection are not treated in the standard MDP setting. In this talk, we focus on the control information and show how it can be combined with the reward measure in a unified way. Both of these measures satisfy the familiar Bellman recursive equations, and their linear combination (the free-energy) provides an interesting new optimization criterion. The tradeoff between value and information, explored using our INFO-RL algorithm, provides a principled justification for stochastic (soft) policies. These optimal policies are also shown to be robust to uncertainties in the reward values by applying the PAC-Bayes generalization bound. The same PAC-Bayesian bounding term thus plays the dual roles of information-gain in the Information-RL formalism and as a model-order regularization term in the learning of the process. |
| 关 键 词: | 马尔可夫决策过程; 优化准则; 贝叶斯正则约束 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2020-06-01：吴雨秋(课程编辑志愿者) |
| 阅读次数: | 69 |