Poster
A Meta-MDP Approach to Exploration for Lifelong Reinforcement Learning
Francisco Garcia · Philip Thomas

Tue Dec 10th 10:45 AM -- 12:45 PM @ East Exhibition Hall B + C #192

In this paper we consider the problem of how a reinforcement learning agent that is tasked with solving a sequence of reinforcement learning problems (a sequence of Markov decision processes) can use knowledge acquired early in its lifetime to improve its ability to solve new problems. We argue that previous experience with similar problems can provide an agent with information about how it should explore when facing a new but related problem. We show that the search for an optimal exploration strategy can be formulated as a reinforcement learning problem itself and demonstrate that such strategy can leverage patterns found in the structure of related problems. We conclude with experiments that show the benefits of optimizing an exploration strategy using our proposed framework.

Author Information

Francisco Garcia (University of Massachusetts - Amherst)
Philip Thomas (University of Massachusetts Amherst)

More from the Same Authors