Automatic Construction of Temporally Extended Actions for MDPs Using Bisimulation Metrics

Abstract

Listen

Translate article

Temporally extended actions are usually effective in speeding up reinforcement learning. In this paper we present a mechanism for automatically constructing such actions, expressed as options [24], in a finite Markov Decision Process (MDP). To do this, we compute a bisimulation metric [7] between the states in a small MDP and the states in a large MDP, which we want to solve. The shape of this metric is then used to completely define a set of options for the large MDP. We demonstrate empirically that our approach is able to improve the speed of reinforcement learning, and is generally not sensitive to parameter tuning.