Attention Option-Critic

Raviteja Chunduru, Doina Precup

Student First Author: Yes

Keywords: Reinforcement learning, hierarchical reinforcement learning, temporal abstraction, options, attention

Abstract: Temporal abstraction in reinforcement learning is the ability of an agent to learn and use high-level behaviors, called options. The option-critic architecture provides a gradient-based end-to-end learning method to construct options. We propose an attention-based extension to this framework, which enables the agent to learn to focus different options on different aspects of the observation space. We show that this leads to behaviorally diverse options which are also capable of state abstraction, and prevents the degeneracy problems of option domination and frequent option switching that occur in option-critic, while achieving a similar sample complexity. We also demonstrate the more interpretable and reusable nature of the learned options in comparison with option-critic through different transfer settings. Experimental results in a relatively simple four-rooms environment and the more complex ALE (Arcade Learning Environment) showcase the efficacy of our approach.