Finite-Time Bounds for Average-Reward Fitted Q-Iteration

Jongmin Lee, Ernest K. Ryu

Keywords: reinforcement learning theory, average-reward MDP, fitted Q-iteration, value iteration, sample complexity, anchoring, single-trajectory data, IID data

TL;DR: We characterize sample complexities for average-reward offline RL with function approximation for weakly communicating MDPs.

Abstract: Although there is an extensive body of work characterizing the sample complexity of discounted-return offline RL with function approximations, prior work on the average-reward setting has received significantly less attention, and existing approaches rely on restrictive assumptions, such as ergodicity or linearity of the MDP. In this work, we establish the first sample complexity results for average-reward offline RL with function approximation for weakly communicating MDPs, a much milder assumption. To this end, we introduce Anchored Fitted Q-Iteration, which combines the standard Fitted Q-Iteration with an anchor mechanism. We show that the anchor, which can be interpreted as a form of weight decay, is crucial for enabling finite-time analysis in the average-reward setting. We also extend our finite-time analysis to the setup where the dataset is generated from a single-trajectory rather than IID transitions, again leveraging the anchor mechanism.

Primary Area: Reinforcement learning (e.g., decision and control, planning, hierarchical RL, robotics)

Submission Number: 22083