Transfer of Samples in Batch Reinforcement Learning

The main objective of transfer learning is to reduce the complexity of learning the solution of a target task by effectively reusing the knowledge retained from solving one or more source tasks. In this paper, we introduce a novel algorithm that transfers samples (i.e., experience tuples ) from source to target tasks. Under the assumption that tasks defined on the same environment often have similar transition models and reward functions, we propose a method to select samples from the source tasks that are mostly similar to the target task, and, then, to use them as input for batch reinforcement learning algorithms. As a result, the number of samples that the agent needs to collect from the target task to learn its solution is reduced. We empirically show that, following the proposed approach, the transfer of samples is effective in reducing the learning complexity, even when the source tasks are significantly different from the target task.