Optimal planning with approximate model-based reinforcement learning
Model-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 opti...
| Main Author: | |
|---|---|
| Language: | English |
| Published: |
University of British Columbia
2012
|
| Online Access: | http://hdl.handle.net/2429/39889 |
| Summary: | Model-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. |
|---|