- Library Home /
- Search Collections /
- Open Collections /
- Browse Collections /
- UBC Theses and Dissertations /
- Model-based active learning in hierarchical policies
Open Collections
UBC Theses and Dissertations
UBC Theses and Dissertations
Model-based active learning in hierarchical policies Cora, Vlad M.
Abstract
Hierarchical task decompositions play an essential role in the design of complex simulation and decision systems, such as the ones that arise in video games. Game designers find it very natural to adopt a divide-and-conquer philosophy of specifying hierarchical policies, where decision modules can be constructed somewhat independently. The process of choosing the parameters of these modules manually is typically lengthy and tedious. The hierarchical reinforcement learning (HRL) field has produced elegant ways of decomposing policies and value functions using semi-Markov decision processes. However, there is still a lack of demonstrations in larger nonlinear systems with discrete and continuous variables. To narrow this gap between industrial practices and academic ideas, we address the problem of designing efficient algorithms to facilitate the deployment of HRL ideas in more realistic settings. In particular, we propose Bayesian active learning methods to learn the relevant aspects of either policies or value functions by focusing on the most relevant parts of the parameter and state spaces respectively. To demonstrate the scalability of our solution, we have applied it to The Open Racing Car Simulator (TORCS), a 3D game engine that implements complex vehicle dynamics. The environment is a large topological map roughly based on downtown Vancouver, British Columbia. Higher level abstract tasks are also learned in this process using a model-based extension of the MAXQ algorithm. Our solution demonstrates how HRL can be scaled to large applications with complex, discrete and continuous non-linear dynamics.
Item Metadata
Title |
Model-based active learning in hierarchical policies
|
Creator | |
Publisher |
University of British Columbia
|
Date Issued |
2008
|
Description |
Hierarchical task decompositions play an essential role in the design of complex simulation and decision systems, such as the ones that arise in video games. Game designers find it very natural to adopt a divide-and-conquer philosophy of specifying hierarchical policies, where decision modules can be constructed somewhat independently. The process of choosing the parameters of these modules manually is typically lengthy and tedious. The hierarchical reinforcement learning (HRL) field has produced elegant ways of decomposing policies and value functions using semi-Markov decision processes. However, there is still a lack of demonstrations in larger nonlinear systems with discrete and continuous variables. To narrow this gap between industrial practices and academic ideas, we address the problem of designing efficient algorithms to facilitate the deployment of HRL ideas in more realistic settings. In particular, we propose Bayesian active learning methods to learn the relevant aspects of either policies or value functions by focusing on the most relevant parts of the parameter and state spaces respectively. To demonstrate the scalability of our solution, we have applied it to The Open Racing Car Simulator (TORCS), a 3D game engine that implements complex vehicle dynamics. The environment is a large topological map roughly based on downtown Vancouver, British Columbia. Higher level abstract tasks are also learned in this process using a model-based extension of the MAXQ algorithm. Our solution demonstrates how HRL can be scaled to large applications with complex, discrete and continuous non-linear dynamics.
|
Extent |
1153699 bytes
|
Genre | |
Type | |
File Format |
application/pdf
|
Language |
eng
|
Date Available |
2008-04-21
|
Provider |
Vancouver : University of British Columbia Library
|
Rights |
Attribution-NonCommercial-NoDerivatives 4.0 International
|
DOI |
10.14288/1.0051276
|
URI | |
Degree | |
Program | |
Affiliation | |
Degree Grantor |
University of British Columbia
|
Graduation Date |
2008-05
|
Campus | |
Scholarly Level |
Graduate
|
Rights URI | |
Aggregated Source Repository |
DSpace
|
Item Media
Item Citations and Data
Rights
Attribution-NonCommercial-NoDerivatives 4.0 International