Policy Generalization In Capacity-Limited Reinforcement Learning

Motivated by the study of generalization in biological intelligence, we examine reinforcement learning (RL) in settings where there are information-theoretic constraints placed on the learner's ability to represent a behavioral policy. We first show that the problem of optimizing expected utility within capacity-limited learning agents maps naturally to the mathematical field of rate-distortion (RD) theory. Applying the RD framework to the RL setting, we develop a new online RL algorithm, Capacity-Limited Actor-Critic, that learns a policy that optimizes a tradeoff between utility maximization and information processing costs. Using this algorithm in a 2D gridworld environment, we demonstrate two novel empirical results. First, at high information rates (high channel capacity), the algorithm achieves faster learning and discovers better policies compared to the standard tabular actor-critic algorithm. Second, we demonstrate that agents with capacity-limited policy representations avoid 'overfitting' and exhibit superior transfer to modified environments, compared to policies learned by agents with unlimited information processing resources. Our work provides a principled framework for the development of computationally rational RL agents.