Extensions of Robbins-Siegmund Theorem with Applications in Reinforcement Learning

• URL: http://arxiv.org/abs/2509.26442v1
• Date: Tue, 30 Sep 2025 16:00:36 GMT
• Title: Extensions of Robbins-Siegmund Theorem with Applications in Reinforcement Learning
• Authors: Xinyu Liu, Zixuan Xie, Shangtong Zhang,
• Abstract summary: We extend the Robbins-Siegmund theorem for almost supermartingales where the zero-order term is not summable but only square summable.<n>We obtain the first almost sure convergence rate, the first high probability concentration bound, and the first $Lp$ convergence rate for $Qp$-learning with linear function.
• Score: 19.81737958703724
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The Robbins-Siegmund theorem establishes the convergence of stochastic processes that are almost supermartingales and is foundational for analyzing a wide range of stochastic iterative algorithms in stochastic approximation and reinforcement learning (RL). However, its original form has a significant limitation as it requires the zero-order term to be summable. In many important RL applications, this summable condition, however, cannot be met. This limitation motivates us to extend the Robbins-Siegmund theorem for almost supermartingales where the zero-order term is not summable but only square summable. Particularly, we introduce a novel and mild assumption on the increments of the stochastic processes. This together with the square summable condition enables an almost sure convergence to a bounded set. Additionally, we further provide almost sure convergence rates, high probability concentration bounds, and $L^p$ convergence rates. We then apply the new results in stochastic approximation and RL. Notably, we obtain the first almost sure convergence rate, the first high probability concentration bound, and the first $L^p$ convergence rate for $Q$-learning with linear function approximation.

Related papers

• Almost Asymptotically Optimal Active Clustering Through Pairwise Observations [59.20614082241528]
  We propose a new analysis framework for clustering $M$ items into an unknown number of $K$ distinct groups using noisy and actively collected responses.<n>We establish a fundamental lower bound on the expected number of queries needed to achieve a desired confidence in the accuracy of the clustering.<n>We develop a computationally feasible variant of the Generalized Likelihood Ratio statistic and show that its performance gap to the lower bound can be accurately empirically estimated.
  arXiv  Detail & Related papers  (2026-02-05T14:16:47Z)
• Finite-Sample Wasserstein Error Bounds and Concentration Inequalities for Nonlinear Stochastic Approximation [6.800624963330628]
  We derive non-asymptotic error bounds for nonlinear approximation algorithms in the Wasserstein-$p$ distance.<n>We show that the normalized last iterates converge to a Gaussian distribution in the $p$-Wasserstein distance at a rate of order $_n1/6$, where $_n$ is the step size.<n>These distributional guarantees imply high-probability concentration inequalities that improve upon those derived from moment bounds and Markovs inequality.
  arXiv  Detail & Related papers  (2026-02-02T18:41:06Z)
• Near-Optimal Clustering in Mixture of Markov Chains [74.3828414695655]
  We study the problem of clustering $T$ trajectories of length $H$, each generated by one of $K$ unknown ergodic Markov chains over a finite state space of size $S$.<n>We derive an instance-dependent, high-probability lower bound on the clustering error rate, governed by the weighted KL divergence between the transition kernels of the chains.<n>We then present a novel two-stage clustering algorithm.
  arXiv  Detail & Related papers  (2025-06-02T05:10:40Z)
• Rethinking the Global Convergence of Softmax Policy Gradient with Linear Function Approximation [52.772454746132276]
  We show that the approximation error in modeling problem-dependent quantities is irrelevant to the algorithm's global convergence.<n>We prove that $textttLin-SPG$ with any arbitrary constant learning rate can ensure global convergence to the optimal policy.
  arXiv  Detail & Related papers  (2025-05-06T04:03:06Z)
• Nonasymptotic CLT and Error Bounds for Two-Time-Scale Stochastic Approximation [12.69327994479157]
  We consider linear two-time-scale approximation algorithms driven by martingale noise.<n>We derive the first non-asymptotic central limit theorem with respect to the Wasserstein-1 distance for two-time-scale approximation with PolyakRuppert averaging.
  arXiv  Detail & Related papers  (2025-02-14T03:20:30Z)
• Towards a Sharp Analysis of Offline Policy Learning for $f$-Divergence-Regularized Contextual Bandits [49.96531901205305]
  We analyze $f$-divergence-regularized offline policy learning.<n>For reverse Kullback-Leibler (KL) divergence, we give the first $tildeO(epsilon-1)$ sample complexity under single-policy concentrability.<n>We extend our analysis to dueling bandits, and we believe these results take a significant step toward a comprehensive understanding of $f$-divergence-regularized policy learning.
  arXiv  Detail & Related papers  (2025-02-09T22:14:45Z)
• Beyond likelihood ratio bias: Nested multi-time-scale stochastic approximation for likelihood-free parameter estimation [49.78792404811239]
  We study inference in simulation-based models where the analytical form of the likelihood is unknown.<n>We use a ratio-free nested multi-time-scale approximation (SA) method that simultaneously tracks the score and drives the parameter update.<n>We show that our algorithm can eliminate the original bias $Obig(sqrtfrac1Nbig)$ and accelerate the convergence rate from $Obig(beta_k+sqrtfracalpha_kNbig)$.
  arXiv  Detail & Related papers  (2024-11-20T02:46:15Z)
• Revisiting the Last-Iterate Convergence of Stochastic Gradient Methods [25.831462008050387]
  The Gradient Descent (SGD) algorithm has triggered people's interest due to its good performance in practice but lack of theoretical understanding. It still remains unclear whether the lastiterate convergence can be provably extended to wider composite optimization and non-Euclidean norms.
  arXiv  Detail & Related papers  (2023-12-13T21:41:06Z)
• High Probability Convergence of Stochastic Gradient Methods [15.829413808059124]
  We show convergence with bounds depending on the initial distance to the optimal solution. We demonstrate that our techniques can be used to obtain high bound for AdaGrad-Norm.
  arXiv  Detail & Related papers  (2023-02-28T18:42:11Z)
• Hessian Averaging in Stochastic Newton Methods Achieves Superlinear Convergence [69.65563161962245]
  We consider a smooth and strongly convex objective function using a Newton method. We show that there exists a universal weighted averaging scheme that transitions to local convergence at an optimal stage.
  arXiv  Detail & Related papers  (2022-04-20T07:14:21Z)
• First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation Approach [57.570201404222935]
  We show that it is possible to obtain regret scaling as $mathcalO(sqrtV_1star K)$ in reinforcement learning with large state spaces. We demonstrate that existing techniques based on at least squares estimation are insufficient to obtain this result.
  arXiv  Detail & Related papers  (2021-12-07T00:29:57Z)
• A Law of Iterated Logarithm for Multi-Agent Reinforcement Learning [3.655021726150368]
  In Multi-Agent Reinforcement Learning (MARL), multiple agents interact with a common environment, as also with each other, for solving a shared problem in sequential decision-making. We derive a novel law of iterated for a family of distributed nonlinear approximation schemes that is useful in MARL.
  arXiv  Detail & Related papers  (2021-10-27T08:01:17Z)
• Finite-Time Analysis for Double Q-learning [50.50058000948908]
  We provide the first non-asymptotic, finite-time analysis for double Q-learning. We show that both synchronous and asynchronous double Q-learning are guaranteed to converge to an $epsilon$-accurate neighborhood of the global optimum.
  arXiv  Detail & Related papers  (2020-09-29T18:48:21Z)
• Reinforcement Learning with General Value Function Approximation: Provably Efficient Approach via Bounded Eluder Dimension [124.7752517531109]
  We establish a provably efficient reinforcement learning algorithm with general value function approximation. We show that our algorithm achieves a regret bound of $widetildeO(mathrmpoly(dH)sqrtT)$ where $d$ is a complexity measure. Our theory generalizes recent progress on RL with linear value function approximation and does not make explicit assumptions on the model of the environment.
  arXiv  Detail & Related papers  (2020-05-21T17:36:09Z)

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.