Skip to main content

Transfer Learning for Policy Search Methods

Matthew E. Taylor‚ Shimon Whiteson and Peter Stone


An ambitious goal of transfer learning is to learn a task faster after training on a different, but related, task. In this paper we extend a previously successful temporal difference approach to transfer in reinforcement learning tasks to work with policy search. In particular, we show how to construct a mapping to translate a population of policies trained via genetic algorithms (GAs) from a source task to a target task. Empirical results in robot soccer Keepaway, a standard RL benchmark domain, demonstrate that transfer via inter-task mapping can markedly reduce the time required to learn a second, more complex, task.

Book Title
ICML 2006: Proceedings of the Twenty−Third International Conference on Machine Learning Transfer Learning Workshop