Reinforcement Learning as (Discrete) Potential Theory
Christopher Connolly
cs.LG cs.GT
Abstract
Reinforcement learning (RL) theory fundamentally depends on probability theory through the Markov chain. There is a deep connection between probability theory and potential theory. This paper reviews that connection and explores the potential-theoretic viewpoint for core reinforcement learning representations and algorithms under a fixed-policy assumption. This viewpoint may offer a path for improved sample efficiency and formal constraints that can be applied to RL. When the fixed-policy assumption is relaxed, the linear potential theory framework can be naturally extended to the nonlinear case.
Topics
Classified with taxonomy v2 on Sat, 5 Sept 2026.