On Rate-Distortion Theory in Capacity-Limited Cognition & Reinforcement Learning
It provides a synthesis for researchers in cognitive science and AI, but is incremental as it reviews existing work without introducing new methods or results.
The paper surveys information-theoretic models that formalize capacity-limited decision-making in cognitive science and reinforcement learning, focusing on how rate-distortion theory enables provably-efficient learning algorithms with Bayesian regret bounds.
Throughout the cognitive-science literature, there is widespread agreement that decision-making agents operating in the real world do so under limited information-processing capabilities and without access to unbounded cognitive or computational resources. Prior work has drawn inspiration from this fact and leveraged an information-theoretic model of such behaviors or policies as communication channels operating under a bounded rate constraint. Meanwhile, a parallel line of work also capitalizes on the same principles from rate-distortion theory to formalize capacity-limited decision making through the notion of a learning target, which facilitates Bayesian regret bounds for provably-efficient learning algorithms. In this paper, we aim to elucidate this latter perspective by presenting a brief survey of these information-theoretic models of capacity-limited decision making in biological and artificial agents.