Contextual Pre-planning on Reward Machine Abstractions for Enhanced Transfer in Deep Reinforcement Learning
This addresses transfer learning challenges in reinforcement learning for AI systems, though it is incremental as it builds on existing reward machine frameworks.
The paper tackles the problem of deep reinforcement learning agents overfitting to training tasks and failing to adapt to minor changes by proposing a method using reward machines to represent tasks with symbolic abstractions, resulting in improved sample efficiency and few-shot transfer across various domains.
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 (RMs), 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. Empirical results show that our representations improve sample efficiency and few-shot transfer in a variety of domains.