# Regret Analysis of Average-Reward Unichain MDPs via an Actor-Critic Approach

arXiv: https://arxiv.org/abs/2505.19986 · HTML: https://mlsanity.com/paper/2505.19986/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in RL theory and sample complexity, one of 15 directions in Deep reinforcement learning methods.
- Builds on 28 of its 48 references that are in the map.
- First posted on arXiv 26 May 2025.

## Placed in

- Deep reinforcement learning methods / [RL theory and sample complexity](https://mlsanity.com/deeprl/rl-theory-and-sample-complexity/)

## Builds on (most cited first, 28 of 28)

- [On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift](https://mlsanity.com/paper/1908.00261/) (2019)
- [Neural Policy Gradient Methods: Global Optimality and Rates of Convergence](https://mlsanity.com/paper/1909.01150/) (2019)
- [Model-free Reinforcement Learning in Infinite-horizon Average-reward Markov Decision Processes](https://mlsanity.com/paper/1910.07072/) (2019)
- [A general sample complexity analysis of vanilla policy gradient](https://mlsanity.com/paper/2107.11433/) (2021)
- [An Improved Analysis of (Variance-Reduced) Policy Gradient and Natural Policy Gradient Methods](https://mlsanity.com/paper/2211.07937/) (2022)
- [Sample Efficient Policy Gradient Methods with Recursive Variance Reduction](https://mlsanity.com/paper/1909.08610/) (2019)
- [An Improved Convergence Analysis of Stochastic Variance-Reduced Policy Gradient](https://mlsanity.com/paper/1905.12615/) (2019)
- [Stochastic Policy Gradient Methods: Improved Sample Complexity for Fisher-non-degenerate Policies](https://mlsanity.com/paper/2302.01734/) (2023)
- [DeepPool: Distributed Model-free Algorithm for Ride-sharing using Deep Reinforcement Learning](https://mlsanity.com/paper/1903.03882/) (2019)
- [Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation](https://mlsanity.com/paper/2007.11849/) (2020)
- [Stochastic first-order methods for average-reward Markov decision processes](https://mlsanity.com/paper/2205.05800/) (2022)
- [Finite-time analysis of single-timescale actor-critic](https://mlsanity.com/paper/2210.09921/) (2022)
- [Near Sample-Optimal Reduction-based Policy Learning for Average Reward MDP](https://mlsanity.com/paper/2212.00603/) (2022)
- [Sharper Model-free Reinforcement Learning for Average-reward Markov Decision Processes](https://mlsanity.com/paper/2306.16394/) (2023)
- [On the Global Optimum Convergence of Momentum-based Policy Gradient](https://mlsanity.com/paper/2110.10116/) (2021)
- [Regret Analysis of Policy Gradient Algorithm for Infinite Horizon Average Reward Markov Decision Processes](https://mlsanity.com/paper/2309.01922/) (2023)
- [Improved Sample Complexity Analysis of Natural Policy Gradient Algorithm with General Parameterization for Infinite Horizon Discounted Reward Markov Decision Processes](https://mlsanity.com/paper/2310.11677/) (2023)
- [Beyond Exponentially Fast Mixing in Average-Reward Reinforcement Learning via Multi-Level Monte Carlo Actor-Critic](https://mlsanity.com/paper/2301.12083/) (2023)
- [Span-Based Optimal Sample Complexity for Weakly Communicating and General Average Reward MDPs](https://mlsanity.com/paper/2403.11477/) (2024)
- [Order-Optimal Regret with Novel Policy Gradient Approaches in Infinite-Horizon Average Reward MDPs](https://mlsanity.com/paper/2404.02108/) (2024)
- [Non-Asymptotic Analysis for Single-Loop (Natural) Actor-Critic with Compatible Function Approximation](https://mlsanity.com/paper/2406.01762/) (2024)
- [Learning General Parameterized Policies for Infinite Horizon Average Reward Constrained MDPs via Primal-Dual Policy Gradient Algorithm](https://mlsanity.com/paper/2402.02042/) (2024)
- [On the Global Convergence of Policy Gradient in Average Reward Markov Decision Processes](https://mlsanity.com/paper/2403.06806/) (2024)
- [Optimistic Q-learning for average reward and episodic reinforcement learning](https://mlsanity.com/paper/2407.13743/) (2024)
- [Global Convergence for Average Reward Constrained MDPs with Primal-Dual Actor Critic Algorithm](https://mlsanity.com/paper/2505.15138/) (2025)
- [Two-Timescale Critic-Actor for Average Reward MDPs with Function Approximation](https://mlsanity.com/paper/2402.01371/) (2024)
- [Learning-based Two-tiered Online Optimization of Region-wide Datacenter Resource Allocation](https://mlsanity.com/paper/2306.17054/) (2023)
- [A Computationally Efficient Algorithm for Infinite-Horizon Average-Reward Linear MDPs](https://mlsanity.com/paper/2504.11997/) (2025)

## Built on by (most cited first, 7 of 7)

- [Efficient Q-Learning and Actor-Critic Methods for Robust Average-Reward Reinforcement Learning](https://mlsanity.com/paper/2506.07040/) (2025)
- [Regret Analysis of Unichain Average Reward Constrained MDPs with General Parameterization](https://mlsanity.com/paper/2602.08000/) (2026)
- [Policy Gradient Algorithms in Average-Reward Multichain MDPs](https://mlsanity.com/paper/2602.18003/) (2026)
- [Learning Policy from a Single Trajectory in Average-Reward Markov Decision Process](https://mlsanity.com/paper/2606.16729/) (2026)
- [Breaking the Bias Barrier in Concave Multi-Objective Reinforcement Learning](https://mlsanity.com/paper/2603.08518/) (2026)
- [Learning Weakly Communicating Average-Reward CMDPs: Strong Duality and Improved Regret](https://mlsanity.com/paper/2605.11586/) (2026)
- [Global Convergence of Average Reward Constrained MDPs with Neural Critic and General Policy Parameterization](https://mlsanity.com/paper/2603.07698/) (2026)

## Abstract (arXiv)

Actor-Critic methods are widely used for their scalability, yet existing theoretical guarantees for infinite-horizon average-reward Markov Decision Processes (MDPs) often rely on restrictive ergodicity assumptions. We propose NAC-B, a Natural Actor-Critic with Batching, that achieves order-optimal regret of tildeO(√T) in infinite-horizon average-reward MDPs under the unichain assumption, which permits both transient states and periodicity. This assumption is among the weakest under which the classic policy gradient theorem remains valid for average-reward settings. NAC-B employs function approximation for both the actor and the critic, enabling scalability to problems with large state and action spaces. The use of batching in our algorithm helps mitigate potential periodicity in the MDP and reduces stochasticity in gradient estimates, and our analysis formalizes these benefits through the introduction of the constants Chit and Ctar, which characterize the rate at which empirical averages over Markovian samples converge to the stationary distribution.