Sciweavers

ATAL
2007
Springer

Transfer via inter-task mappings in policy search reinforcement learning

13 years 11 months ago
Transfer via inter-task mappings in policy search reinforcement learning
The ambitious goal of transfer learning is to accelerate learning on a target task after training on a different, but related, source task. While many past transfer methods have focused on transferring value-functions, this paper presents a method for transferring policies across tasks with different state and action spaces. In particular, this paper utilizes transfer via inter-task mappings for policy search methods (TVITM-PS) to construct a transfer functional that translates a population of neural network policies trained via policy search from a source task to a target task. Empirical results in robot soccer Keepaway and Server Job Scheduling show that TVITM-PS can markedly reduce learning time when full inter-task mappings are available. The results also demonstrate that TVITMPS still succeeds when given only incomplete inter-task mappings. Furthermore, we present a novel method for learning such mappings when they are not available, and give results showing they perform comparab...
Matthew E. Taylor, Shimon Whiteson, Peter Stone
Added 07 Jun 2010
Updated 07 Jun 2010
Type Conference
Year 2007
Where ATAL
Authors Matthew E. Taylor, Shimon Whiteson, Peter Stone
Comments (0)