Bridging the Gap Between Average and Discounted TD Learning

• URL: http://arxiv.org/abs/2605.02103v1
• Date: Sun, 03 May 2026 23:54:36 GMT
• Title: Bridging the Gap Between Average and Discounted TD Learning
• Abstract summary: We introduce a novel algorithm designed explicitly for policy evaluation in the average-reward setting.<n>Our proposed method overcomes previous limitations by guaranteeing convergence to the unique solution of a properly defined Bellman equation.
• Score: 14.556544278062793
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The analysis of Temporal Difference (TD) learning in the average-reward setting faces notable theoretical difficulties because the Bellman operator is not contractive with respect to any norm. This complicates standard analyses of stochastic updates that are effective in discounted settings. Although a considerable body of literature addresses these challenges, existing theoretical approaches come with limitations. We introduce a novel algorithm designed explicitly for policy evaluation in the average-reward setting, utilizing sampling from two Markovian trajectories. Our proposed method overcomes previous limitations by guaranteeing convergence to the unique solution of a properly defined projected Bellman equation. Notably, and in contrast to earlier work, our convergence analysis is uniformly applicable to both linear function approximation and tabular settings and does not involve explicit dimension-dependent terms in its convergence bounds. These results align with what is known to hold in the discounted setting. Furthermore, our algorithm achieves improved dependence on the problem's condition number, reducing the sample complexity from quartic, as in prior literature, to quadratic scaling, and thus matching the efficiency seen in the discounted setting.

Related papers

• Towards Parameter-Free Temporal Difference Learning [16.4999522739561]
  temporal difference (TD) learning is a fundamental algorithm for estimating value functions in reinforcement learning.<n>Recent finite-time analyses of TD with linear function approximation quantify its theoretical convergence rate.<n>We propose a regularized TD(0) algorithm with an exponential step-size schedule.
  arXiv  Detail & Related papers  (2026-03-03T03:49:19Z)
• Bridging Constraints and Stochasticity: A Fully First-Order Method for Stochastic Bilevel Optimization with Linear Constraints [3.567855687957749]
  This work provides the first finite-time convergence guarantees for linearly constrained bilevel optimization using only first-order methods.<n>We address the unprecedented challenge of simultaneously handling linear constraints, noise, and finite-time analysis in bilevel optimization.
  arXiv  Detail & Related papers  (2025-11-13T00:59:20Z)
• Single-loop Algorithms for Stochastic Non-convex Optimization with Weakly-Convex Constraints [49.76332265680669]
  This paper examines a crucial subset of problems where both the objective and constraint functions are weakly convex.<n>Existing methods often face limitations, including slow convergence rates or reliance on double-loop designs.<n>We introduce a novel single-loop penalty-based algorithm to overcome these challenges.
  arXiv  Detail & Related papers  (2025-04-21T17:15:48Z)
• Achieving $\widetilde{\mathcal{O}}(\sqrt{T})$ Regret in Average-Reward POMDPs with Known Observation Models [69.1820058966619]
  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)
• Learning to Optimize with Stochastic Dominance Constraints [103.26714928625582]
  In this paper, we develop a simple yet efficient approach for the problem of comparing uncertain quantities. We recast inner optimization in the Lagrangian as a learning problem for surrogate approximation, which bypasses apparent intractability. The proposed light-SD demonstrates superior performance on several representative problems ranging from finance to supply chain management.
  arXiv  Detail & Related papers  (2022-11-14T21:54:31Z)
• The Stochastic Proximal Distance Algorithm [5.3315823983402755]
  We propose and analyze a class of iterative optimization methods that recover a desired constrained estimation problem as a penalty parameter. We extend recent theoretical devices to establish finite error bounds and a complete characterization of convergence rates. We validate our analysis via a thorough empirical study, also showing that unsurprisingly, the proposed method outpaces batch versions on popular learning tasks.
  arXiv  Detail & Related papers  (2022-10-21T22:07:28Z)
• Optimal variance-reduced stochastic approximation in Banach spaces [114.8734960258221]
  We study the problem of estimating the fixed point of a contractive operator defined on a separable Banach space. We establish non-asymptotic bounds for both the operator defect and the estimation error.
  arXiv  Detail & Related papers  (2022-01-21T02:46:57Z)
• Accelerated and instance-optimal policy evaluation with linear function approximation [17.995515643150657]
  Existing algorithms fail to match at least one of these lower bounds. We develop an accelerated, variance-reduced fast temporal difference algorithm that simultaneously matches both lower bounds and attains a strong notion of instance-optimality.
  arXiv  Detail & Related papers  (2021-12-24T17:21:04Z)
• Stochastic Gradient Descent-Ascent and Consensus Optimization for Smooth Games: Convergence Analysis under Expected Co-coercivity [49.66890309455787]
  We introduce the expected co-coercivity condition, explain its benefits, and provide the first last-iterate convergence guarantees of SGDA and SCO. We prove linear convergence of both methods to a neighborhood of the solution when they use constant step-size. Our convergence guarantees hold under the arbitrary sampling paradigm, and we give insights into the complexity of minibatching.
  arXiv  Detail & Related papers  (2021-06-30T18:32:46Z)
• On the Convergence of Stochastic Extragradient for Bilinear Games with Restarted Iteration Averaging [96.13485146617322]
  We present an analysis of the ExtraGradient (SEG) method with constant step size, and present variations of the method that yield favorable convergence. We prove that when augmented with averaging, SEG provably converges to the Nash equilibrium, and such a rate is provably accelerated by incorporating a scheduled restarting procedure.
  arXiv  Detail & Related papers  (2021-06-30T17:51:36Z)

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.