Heterogeneous and Hierarchical Cooperative Learning via Combining Decision Trees
Metadata only
Date
2006Type
- Conference Paper
ETH Bibliography
yes
Altmetrics
Abstract
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 Show more
Publication status
publishedExternal links
Book title
2006 IEEE/RSJ International Conference on Intelligent Robots and SystemsPages / Article No.
Publisher
IEEEEvent
Organisational unit
03737 - Siegwart, Roland Y. / Siegwart, Roland Y.
More
Show all metadata
ETH Bibliography
yes
Altmetrics