Using Bisimulation for Policy Transfer in MDPs

10 years 4 days ago
Using Bisimulation for Policy Transfer in MDPs
Knowledge transfer has been suggested as a useful approach for solving large Markov Decision Processes. The main idea is to compute a decision-making policy in one environment and use it in a different environment, provided the two are "close enough". In this paper, we use bisimulation-style metrics (Ferns et al., 2004) to guide knowledge transfer. We propose algorithms that decide what actions to transfer from the policy computed on a small MDP task to a large task, given the bisimulation distance between states in the two tasks. We demonstrate the inherent "pessimism" of bisimulation metrics and present variants of this metric aimed to overcome this pessimism, leading to improved action transfer. We also show that using this approach for transferring temporally extended actions (Sutton et al., 1999) is more successful than using it exclusively with primitive actions. We present theoretical guarantees on the quality of the transferred policy, as well as promising ...
Pablo Samuel Castro, Doina Precup
Added 29 Oct 2010
Updated 29 Oct 2010
Type Conference
Year 2010
Where AAAI
Authors Pablo Samuel Castro, Doina Precup
Comments (0)