Safe option-critic: Learning safety in the option-critic architecture

Abstract

Designing hierarchical reinforcement learning algorithms that exhibit safe behaviour is not only vital for practical applications but also facilitates a better understanding of an agent's decisions. We tackle this problem in the options framework (Sutton, Precup & Singh, 1999), a particular way to specify temporally abstract actions which allow an agent to use sub-policies with start and end conditions. We consider a behaviour as safe that avoids regions of state space with high uncertainty in the outcomes of actions. We propose an optimization objective that learns safe options by encouraging the agent to visit states with higher behavioural consistency. The proposed objective results in a trade-off between maximizing the standard expected return and minimizing the effect of model uncertainty in the return. We propose a policy gradient algorithm to optimize the constrained objective function. We examine the quantitative and qualitative behaviours of the proposed approach in a tabular grid world, continuous-state puddle world, and three games from the Arcade Learning Environment: Ms. Pacman, Amidar, and QBert. Our approach achieves a reduction in the variance of return, boosts performance in environments with intrinsic variability in the reward structure, and compares favourably both with primitive actions and with riskneutral options.