Conference proceeding
Behavior transfer for value-function-based reinforcement learning
Proceedings of the fourth international joint conference on autonomous agents and multiagent systems, pp.53-59
AAMAS '05
07/25/2005
Handle:
https://hdl.handle.net/2376/107679
Abstract
Temporal difference (TD) learning methods [22] have become popular reinforcement learning techniques in recent years. TD methods have had some experimental successes and have been shown to exhibit some desirable properties in theory, but have often been found very slow in practice. A key feature of TD methods is that they represent policies in terms of value functions. In this paper we introduce behavior transfer , a novel approach to speeding up TD learning by transferring the learned value function from one task to a second related task. We present experimental results showing that autonomous learners are able to learn one multiagent task and then use behavior transfer to markedly reduce the total training time for a more complex task.
Metrics
6 Record Views
Details
- Title
- Behavior transfer for value-function-based reinforcement learning
- Creators
- Matthew TaylorPeter Stone
- Publication Details
- Proceedings of the fourth international joint conference on autonomous agents and multiagent systems, pp.53-59
- Academic Unit
- Electrical Engineering and Computer Science, School of
- Series
- AAMAS '05
- Publisher
- ACM
- Identifiers
- 99900547023001842
- Language
- English
- Resource Type
- Conference proceeding