Heterogeneous and Hierarchical Cooperative Learning via Combining Decision Trees

Decision trees, being human readable and hierarchically structured, provide a suitable mean to derive state-space abstraction and simplify the inclusion of the available knowledge for a reinforcement learning (RL) agent. In this paper, we address two approaches to combine and purify the available kn...

Full description

Saved in:
Bibliographic Details
Published in2006 IEEE/RSJ International Conference on Intelligent Robots and Systems pp. 2684 - 2690
Main Authors Asadpour, M., Ahmadabadi, M.N., Siegwart, R.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.10.2006
Subjects
Control systems
Decision trees
Humans
Intelligent agent
Intelligent control
Intelligent robots
Intelligent structures
Learning systems
Multiagent systems
Process control
Online AccessGet full text

Cover

More Information
Summary:Decision trees, being human readable and hierarchically structured, provide a suitable mean to derive state-space abstraction and simplify the inclusion of the available knowledge for a reinforcement learning (RL) agent. In this paper, we address two approaches to combine and purify the available knowledge in the abstraction trees, stored among different RL agents in a multi-agent system, or among the decision trees learned by the same agent using different methods. Simulation results in nondeterministic football learning task provide strong evidences for enhancement in convergence rate and policy performance
ISBN:9781424402588
1424402581
ISSN:2153-0858
2153-0866
DOI:10.1109/IROS.2006.281990