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.