Matthew E. Taylor, Peter Stone
A key component of any reinforcement learning (RL) algorithm is the underlying representation used by the agent for learning (e.g. the parameterization of its function approximator). Transfer learning tasks typically look at speeding up a target task after learning in a source task. This paper considers a different, but related, question: is it possible, and desirable, for agents to transfer from a source representation to a target representation? Elaboration, presented below, is a representation transfer (RT) algorithm that may allow an agent to learn faster than learning with a single representation.
Subjects: 12.1 Reinforcement Learning; Please choose a second document classification
Submitted: Apr 9, 2007