图 书 馆
班迪特反馈下的在线马尔可夫决策过程Online Markov Decision Processes under Bandit Feedback |
|
| 课程网址: | http://videolectures.net/nips2010_neu_omd/ |
| 主讲教师: | Gergely Neu |
| 开课单位: | 北欧里尔公司 |
| 开课时间: | 2011-03-25 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | We consider online learning in finite stochastic Markovian environments where in each time step a new reward function is chosen by an oblivious adversary. The goal of the learning agent is to compete with the best stationary policy in terms of the total reward received. In each time step the agent observes the current state and the reward associated with the last transition, however, the agent does not observe the rewards associated with other state-action pairs. The agent is assumed to know the transition probabilities. The state of the art result for this setting is a no-regret algorithm. In this paper we propose a new learning algorithm and assuming that stationary policies mix uniformly fast, we show that after T time steps, the expected regret of the new algorithm is O(T^{2/3} (ln T)^{1/3}), giving the first rigorously proved convergence rate result for the problem. |
| 关 键 词: | 马尔可夫环境 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2019-07-26：cwx |
| 阅读次数: | 59 |