图 书 馆
自举技巧Bootstrapping Skills |
|
| 课程网址: | http://videolectures.net/rldm2015_mankowitz_bootstrapping_skills/ |
| 主讲教师: | Daniel Mankowitz |
| 开课单位: | 以色列理工学院 |
| 开课时间: | 2015-07-28 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | The monolithic approach to policy representation in Markov Decision Processes (MDPs) looks for a single policy that can be represented as a function from states to actions. For the monolithic approach to succeed (and this is not always possible), a complex feature representation is often necessary since the policy is a complex object that has to prescribe what actions to take all over the state space. This is especially true 11 in large-state MDP domains with complicated dynamics. It is also computationally inefficient to both learn and plan in MDPs using a complex monolithic approach. We present a different approach where we restrict the policy space to policies that can be represented as combinations of simpler, parameterized skills—a type of temporally extended action, with a simple policy representation. We introduce Learning Skills via Bootstrapping (LSB) that can use a broad family of Reinforcement Learning (RL) algorithms as a “black box” to iteratively learn parametrized skills. Initially, the learned skills are short-sighted, but each iteration of the algorithm allows the skills to bootstrap off one another, improving each skill in the process. We prove that this bootstrapping process returns a near-optimal policy. Furthermore, our experiments demonstrate that LSB can solve MDPs that, given the same representational power, could not be solved by a monolithic approach. Thus, planning with learned skills results in better policies without requiring complex policy representations. |
| 关 键 词: | 算法; 强化学习; 策略 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2020-12-14：yxd |
| 最后编审: | 2020-12-14：yxd |
| 阅读次数: | 39 |