University of British Columbia
Optimal planning with approximate model-based reinforcement learning
Abstract
dc:descriptionModel-based reinforcement learning methods make efficient use of samples by building a model of the environment and planning with it. Compared to model-free methods, they usually take fewer samples to converge to the optimal policy. Despite that efficiency, model-based methods may not learn the optimal policy due to structural modeling assumptions. In this thesis, we show that by combining model- based methods with hierarchically optimal recursive Q-learning (HORDQ) under a hierarchical reinforcement learning framework, the proposed approach learns the optimal policy even when the assumptions of the model are not all satisfied. The effectiveness of our approach is demonstrated with the Bus domain and Infinite Mario – a Java implementation of Nintendo’s Super Mario Brothers.
Degree
thesis:*- Name thesis:degree_name
- Master of Science - MSc
- Level thesis:degree_level
- master's
- Discipline thesis:degree_discipline
- Computer Science
- Grantor dc:publisher
- University of British Columbia
- Year dc:date
- 2011
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Kao, Hai Feng
Rights
dc:rights- Statement dc:rights
-
- Attribution-ShareAlike 3.0 Unported
- Language dc:language
- eng
Identifiers
dc:identifier.*- Handle dc:identifier
- http://hdl.handle.net/2429/39889