Contextual Pre-Planning on Reward Machine Abstractions for Enhanced Transfer in Deep Reinforcement Learning

Guy Azran, Mohamad Hosein Danesh, Stefano V Albrecht, Sarah Keren

Keywords: Deep Reinforcement Learning, Transfer Learning, Model-Based Reinforcement Learning

TL;DR: Enhancing transfer learning by leveraging optimal transitions in reward machine abstractions

Abstract: Recent studies show that deep reinforcement learning (DRL) agents tend to overfit to the task on which they were trained and fail to adapt to minor environment changes. To expedite learning when transferring to unseen tasks, we propose a novel approach to representing the current task using reward machines (RM), state machine abstractions that induce subtasks based on the current task’s rewards and dynamics. Our method provides agents with symbolic representations of optimal transitions from their current abstract state and rewards them for achieving these transitions. These representations are shared across tasks, allowing agents to exploit knowledge of previously encountered symbols and transitions, thus enhancing transfer. Our empirical evaluation shows that our representations improve sample efficiency and few-shot transfer in a variety of domains.

Submission Number: 11