Transfer in Reinforcement Learning via Markov Logic Networks

We propose the use of statistical relational learning, and in particular the formalism of Markov Logic Networks, for transfer in reinforcement learning. Our goal is to ex- tract relational knowledge from a source task and use it to speed up learning in a related target task. We do so by learning a Markov Logic Network that describes the source-task Q-function, and then using it for decision making in the early learning stages of the target task. Through experiments in the RoboCup simulated-soccer domain, we show that this approach can provide a sub- stantial performance benet in the target task.