Google Research

There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learning

NeurIPS (2021)


We propose to learn to distinguish reversible from irreversible actions for better informed decision-making in Reinforcement Learning (RL). From theoretical considerations, we show that approximate reversibility can be learned through a simple surrogate task: ranking randomly sampled trajectory events in chronological order. Intuitively, pairs of events that are always observed in the same order are likely to be separated by an irreversible sequence of actions. Conveniently, learning the temporal order of events can be done in a fully self-supervised way, and we learn the reversibility of actions from pure experience, without any priors. We propose two different strategies that incorporate reversibility in RL agents, one strategy for exploration (RAE) and one strategy for control (RAC). We demonstrate the potential of reversibility-aware agents in several tasks including safe RL tasks, and the challenging Sokoban game.

Research Areas

Learn more about how we do research

We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work