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

• URL: http://arxiv.org/abs/2505.19986v1
• Date: Mon, 26 May 2025 13:43:02 GMT
• Title: Regret Analysis of Average-Reward Unichain MDPs via an Actor-Critic Approach
• Authors: Swetha Ganesh, Vaneet Aggarwal,
• Abstract summary: We propose a Natural Actor-Critic with order-optimal regret of $tildeO(sqrtT)$ in infinite-reward average-reward Decision Processes.<n> NACB employs function approximation for both actor and the critic, enabling scalability to large state potential periodicity and action spaces.
• Score: 33.38582292895673
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 $\tilde{O}(\sqrt{T})$ 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 $C_{\text{hit}}$ and $C_{\text{tar}}$, which characterize the rate at which empirical averages over Markovian samples converge to the stationary distribution.

Related papers

• Finite-Sample Analysis of Policy Evaluation for Robust Average Reward Reinforcement Learning [33.71515983281633]
  We present first finite-sample analysis for policy evaluation in robust average-rewards.<n>Our approach builds upon Multi-Level Monte Carlo (MLMC) techniques to estimate the robust Bellman operator efficiently.<n>Our method achieves the order-optimal sample complexity of $tildemathcalO(epsilon-2)$ for robust policy evaluation and robust average reward estimation.
  arXiv  Detail & Related papers  (2025-02-24T03:55:09Z)
• Achieving $\widetilde{\mathcal{O}}(\sqrt{T})$ Regret in Average-Reward POMDPs with Known Observation Models [56.92178753201331]
  We tackle average-reward infinite-horizon POMDPs with an unknown transition model.<n>We present a novel and simple estimator that overcomes this barrier.
  arXiv  Detail & Related papers  (2025-01-30T22:29:41Z)
• Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes [44.974100402600165]
  We study the evaluation of a policy best-parametric and worst-case perturbations to a decision process (MDP) We use transition observations from the original MDP, whether they are generated under the same or a different policy. Our estimator is also estimated statistical inference using Wald confidence intervals.
  arXiv  Detail & Related papers  (2024-03-29T18:11:49Z)
• Towards Global Optimality for Practical Average Reward Reinforcement Learning without Mixing Time Oracles [83.85151306138007]
  Multi-level Actor-Critic (MAC) framework incorporates a Multi-level Monte-Carlo (MLMC) estimator. We demonstrate that MAC outperforms the existing state-of-the-art policy gradient-based method for average reward settings.
  arXiv  Detail & Related papers  (2024-03-18T16:23:47Z)
• On the Global Convergence of Policy Gradient in Average Reward Markov Decision Processes [50.68789924454235]
  We present the first finite time global convergence analysis of policy gradient in the context of average reward Markov decision processes (MDPs) Our analysis shows that the policy gradient iterates converge to the optimal policy at a sublinear rate of $Oleft(frac1Tright),$ which translates to $Oleft(log(T)right)$ regret, where $T$ represents the number of iterations.
  arXiv  Detail & Related papers  (2024-03-11T15:25:03Z)
• Off-Policy Evaluation in Markov Decision Processes under Weak Distributional Overlap [5.0401589279256065]
  We re-visit the task of off-policy evaluation in Markov decision processes (MDPs) under a weaker notion of distributional overlap. We introduce a class of truncated doubly robust (TDR) estimators which we find to perform well in this setting.
  arXiv  Detail & Related papers  (2024-02-13T03:55:56Z)
• Beyond Exponentially Fast Mixing in Average-Reward Reinforcement Learning via Multi-Level Monte Carlo Actor-Critic [61.968469104271676]
  We propose an RL methodology attuned to the mixing time by employing a multi-level Monte Carlo estimator for the critic, the actor, and the average reward embedded within an actor-critic (AC) algorithm. We experimentally show that these alleviated restrictions on the technical conditions required for stability translate to superior performance in practice for RL problems with sparse rewards.
  arXiv  Detail & Related papers  (2023-01-28T04:12:56Z)
• Latent State Marginalization as a Low-cost Approach for Improving Exploration [79.12247903178934]
  We propose the adoption of latent variable policies within the MaxEnt framework. We show that latent variable policies naturally emerges under the use of world models with a latent belief state. We experimentally validate our method on continuous control tasks, showing that effective marginalization can lead to better exploration and more robust training.
  arXiv  Detail & Related papers  (2022-10-03T15:09:12Z)
• Optimal policy evaluation using kernel-based temporal difference methods [78.83926562536791]
  We use kernel Hilbert spaces for estimating the value function of an infinite-horizon discounted Markov reward process. We derive a non-asymptotic upper bound on the error with explicit dependence on the eigenvalues of the associated kernel operator. We prove minimax lower bounds over sub-classes of MRPs.
  arXiv  Detail & Related papers  (2021-09-24T14:48:20Z)
• Amortized Conditional Normalized Maximum Likelihood: Reliable Out of Distribution Uncertainty Estimation [99.92568326314667]
  We propose the amortized conditional normalized maximum likelihood (ACNML) method as a scalable general-purpose approach for uncertainty estimation. Our algorithm builds on the conditional normalized maximum likelihood (CNML) coding scheme, which has minimax optimal properties according to the minimum description length principle. We demonstrate that ACNML compares favorably to a number of prior techniques for uncertainty estimation in terms of calibration on out-of-distribution inputs.
  arXiv  Detail & Related papers  (2020-11-05T08:04:34Z)
• Asymptotically Efficient Off-Policy Evaluation for Tabular Reinforcement Learning [20.546806161935578]
  We consider the problem of off-policy evaluation for reinforcement learning. The goal is to estimate the expected reward of a target policy using offline data collected by running a logging policy. We show that a marginalized importance sampling (MIS) approach can be used to achieve an estimation error of order $O(H3/ n)$ in mean square error.
  arXiv  Detail & Related papers  (2020-01-29T09:56:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.