On Convergence Of Average-reward Off-policy Control Algorithms In Weakly Communicating Mdps

Abstract

We show two average-reward off-policy control algorithms, Differential Q-learning (Wan, Naik, & Sutton 2021a) and RVI Q-learning (Abounadi Bertsekas & Borkar 2001), converge in weakly communicating MDPs. Weakly communicating MDPs are the most general MDPs that can be solved by a learning algorithm with a single stream of experience. The original convergence proofs of the two algorithms require that the solution set of the average-reward optimality equation only has one degree of freedom, which is not necessarily true for weakly communicating MDPs. To the best of our knowledge, our results are the first showing average-reward off-policy control algorithms converge in weakly communicating MDPs. As a direct extension, we show that average-reward options algorithms for temporal abstraction introduced by Wan, Naik, & Sutton (2021b) converge if the Semi-MDP induced by options is weakly communicating.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywan2022on

Related papers

• Learning And Planning In Average-reward Markov Decision Processes (2020)0.00
• A Sharper Global Convergence Analysis For Average Reward Reinforcement Learning Via An Actor-critic Approach (2024)0.00
• Planning And Learning In Average Risk-aware Mdps (2025)0.00
• Revisiting Value Iteration: Unified Analysis Of Discounted And Average-reward Cases (2025)0.00
• Stochastic First-order Methods For Average-reward Markov Decision Processes (2022)3.58
• From Set Convergence To Pointwise Convergence: Finite-time Guarantees For Average-reward Q-learning With Adaptive Stepsizes (2025)0.00
• Optimal Single-policy Sample Complexity And Transient Coverage For Average-reward Offline RL (2025)0.00
• Linear-quadratic Mean-field Reinforcement Learning: Convergence Of Policy Gradient Methods (2019)0.00