On Convergence of Average-Reward Off-Policy Control Algorithms in Weakly Communicating MDPs
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 2 of its 20 references that are in the map. First posted on arXiv 30 Sep 2022.
Builds on
2 of 20 references.
References · 2
- 2020Learning and Planning in Average-Reward Markov Decision Processescited by 54
- 2021Average-Reward Learning and Planning with Optionscited by 8
Built on by
Citing papers per year: 2023: 1; 2024: 1; 2025: 2; 2026: 1.
5 papers.
- 2023Model-Free Robust Average-Reward Reinforcement Learningcited by 20
- 2024RVI-SAC: Average Reward Off-Policy Deep Reinforcement Learningcited by 5
- 2025Model-Free Robust Average-Reward Reinforcement Learning with Sample Complexity Analysiscited by 2
- 2026Position: Deployed Reinforcement Learning should be Continualcited by 1
- 2025Average Reward Reinforcement Learning for Omega-Regular and Mean-Payoff Objectivescited by 0
- 2026Position: Deployed Reinforcement Learning should be Continual1 Jun 2026
- 2025Average Reward Reinforcement Learning for Omega-Regular and Mean-Payoff Objectives21 May 2025
- 2025Model-Free Robust Average-Reward Reinforcement Learning with Sample Complexity Analysis18 May 2025
- 2024RVI-SAC: Average Reward Off-Policy Deep Reinforcement Learning4 Aug 2024
- 2023Model-Free Robust Average-Reward Reinforcement Learning17 May 2023