Improving Action Selection in MDP's via Knowledge Transfer

Temporal-difference reinforcement learning (RL) has been successfully applied in several domains with large state sets. Large action sets, however, have received considerably less attention. This paper demonstrates the use of knowledge transfer between related tasks to accelerate learning with large action sets. We introduce action transfer, a technique that extracts the actions from the (near-)optimal solution to the first task and uses them in place of the full action set when learning any subsequent tasks. When optimal actions make up a small fraction of the domain's action set, action transfer can substantially reduce the number of actions and thus the complexity of the problem. However, action transfer between dissimilar tasks can be detrimental. To address this difficulty, we contribute randomized task perturbation (RTP), an enhancement to action transfer that makes it robust to unrepresentative source tasks. We motivate RTP action transfer with a detailed theoretical analysis featuring a formalism of related tasks and a bound on the suboptimality of action transfer. The empirical results in this paper show the potential of RTP action transfer to substantially expand the applicability of RL to problems with large action sets.