Vishal Soni, Satinder Singh Baveja
We examine the problem of Transfer in Reinforcement Learning and present a method to utilize knowledge acquired in one Markov Decision Process (MDP) to bootstrap learning in a more complex but related MDP. We build on work in model minimization in Reinforcement Learning to define relationships between state-action pairs of the two MDPs. Our main contribution in this work is to provide a way to compactly represent such mappings using relationships between state variables in the two domains. We use these functions to transfer a learned policy in the first domain into an option in the new domain, and apply intra-option learning methods to bootstrap learning in the new domain. We first evaluate our approach in the well known Blocksworld domain. We then demonstrate that our approach to transfer is viable in a complex domain with a continuous state space by evaluating it in the Robosoccer Keepaway domain.
Subjects: 12.1 Reinforcement Learning