Stochastic Approximation with Unbounded Markovian Noise: A General-Purpose Theorem

• URL: http://arxiv.org/abs/2410.21704v1
• Date: Tue, 29 Oct 2024 03:40:53 GMT
• Title: Stochastic Approximation with Unbounded Markovian Noise: A General-Purpose Theorem
• Authors: Shaan Ul Haque, Siva Theja Maguluri,
• Abstract summary: We consider average-reward Reinforcement Learning with unbounded state space and reward function. Recent works studied this problem in the actor-critic framework. We study Temporal Difference (TD) learning with linear function approximation.
• Score: 7.443139252028032
• License:
• Abstract: Motivated by engineering applications such as resource allocation in networks and inventory systems, we consider average-reward Reinforcement Learning with unbounded state space and reward function. Recent works studied this problem in the actor-critic framework and established finite sample bounds assuming access to a critic with certain error guarantees. We complement their work by studying Temporal Difference (TD) learning with linear function approximation and establishing finite-time bounds with the optimal $\mathcal{O}\left(1/\epsilon^2\right)$ sample complexity. These results are obtained using the following general-purpose theorem for non-linear Stochastic Approximation (SA). Suppose that one constructs a Lyapunov function for a non-linear SA with certain drift condition. Then, our theorem establishes finite-time bounds when this SA is driven by unbounded Markovian noise under suitable conditions. It serves as a black box tool to generalize sample guarantees on SA from i.i.d. or martingale difference case to potentially unbounded Markovian noise. The generality and the mild assumption of the setup enables broad applicability of our theorem. We illustrate its power by studying two more systems: (i) We improve upon the finite-time bounds of $Q$-learning by tightening the error bounds and also allowing for a larger class of behavior policies. (ii) We establish the first ever finite-time bounds for distributed stochastic optimization of high-dimensional smooth strongly convex function using cyclic block coordinate descent.

Related papers

• Stochastic Approximation with Delayed Updates: Finite-Time Rates under Markovian Sampling [73.5602474095954]
  We study the non-asymptotic performance of approximation schemes with delayed updates under Markovian sampling. Our theoretical findings shed light on the finite-time effects of delays for a broad class of algorithms.
  arXiv  Detail & Related papers  (2024-02-19T03:08:02Z)
• The Curse of Memory in Stochastic Approximation: Extended Version [1.534667887016089]
  Theory and application of approximation (SA) has grown within the control systems community since the earliest days of adaptive control. Recent results establish remarkable performance of SA with (sufficiently small) constant step-size $alpha>0$.
  arXiv  Detail & Related papers  (2023-09-06T12:22:32Z)
• Stochastic Inexact Augmented Lagrangian Method for Nonconvex Expectation Constrained Optimization [88.0031283949404]
  Many real-world problems have complicated non functional constraints and use a large number of data points. Our proposed method outperforms an existing method with the previously best-known result.
  arXiv  Detail & Related papers  (2022-12-19T14:48:54Z)
• 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)
• Concave Utility Reinforcement Learning with Zero-Constraint Violations [43.29210413964558]
  We consider the problem of concave utility reinforcement learning (CURL) with convex constraints. We propose a model-based learning algorithm that also achieves zero constraint violations.
  arXiv  Detail & Related papers  (2021-09-12T06:13:33Z)
• High Probability Complexity Bounds for Non-Smooth Stochastic Optimization with Heavy-Tailed Noise [51.31435087414348]
  It is essential to theoretically guarantee that algorithms provide small objective residual with high probability. Existing methods for non-smooth convex optimization have complexity bounds with dependence on confidence level. We propose novel stepsize rules for two methods with gradient clipping.
  arXiv  Detail & Related papers  (2021-06-10T17:54:21Z)
• Optimal oracle inequalities for solving projected fixed-point equations [53.31620399640334]
  We study methods that use a collection of random observations to compute approximate solutions by searching over a known low-dimensional subspace of the Hilbert space. We show how our results precisely characterize the error of a class of temporal difference learning methods for the policy evaluation problem with linear function approximation.
  arXiv  Detail & Related papers  (2020-12-09T20:19:32Z)
• On Linear Stochastic Approximation: Fine-grained Polyak-Ruppert and Non-Asymptotic Concentration [115.1954841020189]
  We study the inequality and non-asymptotic properties of approximation procedures with Polyak-Ruppert averaging. We prove a central limit theorem (CLT) for the averaged iterates with fixed step size and number of iterations going to infinity.
  arXiv  Detail & Related papers  (2020-04-09T17:54:18Z)
• Stochastic Approximation with Markov Noise: Analysis and applications in reinforcement learning [0.0]
  We present for the first time an convergence analysis of two time-scale approximation driven by "controlled" Markov noise. We analyze the behavior of our framework by relating it to limiting differential inclusions in both time scales. We obtain the first informative error bounds on function approximation for the policy evaluation algorithm.
  arXiv  Detail & Related papers  (2020-04-08T03:59:21Z)
• Finite-Sample Analysis of Stochastic Approximation Using Smooth Convex Envelopes [40.31139355952393]
  We construct a smooth Lyapunov function using the generalized envelope, and show that the iterates of SA have negative drift with respect to that Lyapunov function. In particular, we use it to establish the first-known convergence rate of the V-trace algorithm for off-policy TD-learning. We also use it to study TD-learning in the on-policy setting, and recover the existing state-of-the-art results for $Q$-learning.
  arXiv  Detail & Related papers  (2020-02-03T16:42:01Z)

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.