Two-Timescale Critic-Actor for Average Reward MDPs with Function Approximation

• URL: http://arxiv.org/abs/2402.01371v2
• Date: Fri, 24 May 2024 06:57:17 GMT
• Title: Two-Timescale Critic-Actor for Average Reward MDPs with Function Approximation
• Authors: Prashansa Panda, Shalabh Bhatnagar,
• Abstract summary: We present the first two-timescale critic-actor algorithm with function approximation in the long-run average reward setting. A notable feature of our analysis is that unlike recent single-timescale actor-critic algorithms, we present a complete convergence analysis of our scheme.
• Score: 5.945710235932345
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In recent years, there has been a lot of research activity focused on carrying out non-asymptotic convergence analyses for actor-critic algorithms. Recently a two-timescale critic-actor algorithm has been presented for the discounted cost setting in the look-up table case where the timescales of the actor and the critic are reversed and only asymptotic convergence shown. In our work, we present the first two-timescale critic-actor algorithm with function approximation in the long-run average reward setting and present the first finite-time non-asymptotic as well as asymptotic convergence analysis for such a scheme. We obtain optimal learning rates and prove that our algorithm achieves a sample complexity of $\mathcal{\tilde{O}}(\epsilon^{-2.08})$ for the mean squared error of the critic to be upper bounded by $\epsilon$ which is better than the one obtained for two-timescale actor-critic in a similar setting. A notable feature of our analysis is that unlike recent single-timescale actor-critic algorithms, we present a complete asymptotic convergence analysis of our scheme in addition to the finite-time bounds that we obtain and show that the (slower) critic recursion converges asymptotically to the attractor of an associated differential inclusion with actor parameters corresponding to local maxima of a perturbed average reward objective. We also show the results of numerical experiments on three benchmark settings and observe that our critic-actor algorithm performs on par and is in fact better than the other algorithms considered.

Related papers

• Improved Sample Complexity for Global Convergence of Actor-Critic Algorithms [49.19842488693726]
  We establish the global convergence of the actor-critic algorithm with a significantly improved sample complexity of $O(epsilon-3)$. Our findings provide theoretical support for many algorithms that rely on constant step sizes.
  arXiv  Detail & Related papers  (2024-10-11T14:46:29Z)
• Non-Asymptotic Analysis for Single-Loop (Natural) Actor-Critic with Compatible Function Approximation [18.77565744533582]
  Actor-critic (AC) is a powerful method for learning an optimal policy in reinforcement learning. AC converges to an $epsilon+varepsilon_textcritic$ neighborhood of stationary points with the best known sample complexity. This paper analyzes the convergence of both AC and NAC algorithms with compatible function approximation.
  arXiv  Detail & Related papers  (2024-06-03T20:05:04Z)
• Finite-Time Analysis of Three-Timescale Constrained Actor-Critic and Constrained Natural Actor-Critic Algorithms [5.945710235932345]
  We consider actor critic and natural actor critic algorithms with function approximation for constrained Markov decision processes. We carry out a non-asymptotic analysis for both of these algorithms in a non-i.i.d (Markovian) setting. We also show the results of experiments on three different Safety-Gym environments.
  arXiv  Detail & Related papers  (2023-10-25T05:04:00Z)
• Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality [131.45028999325797]
  We develop a doubly robust off-policy AC (DR-Off-PAC) for discounted MDP. DR-Off-PAC adopts a single timescale structure, in which both actor and critics are updated simultaneously with constant stepsize. We study the finite-time convergence rate and characterize the sample complexity for DR-Off-PAC to attain an $epsilon$-accurate optimal policy.
  arXiv  Detail & Related papers  (2021-02-23T18:56:13Z)
• ROOT-SGD: Sharp Nonasymptotics and Near-Optimal Asymptotics in a Single Algorithm [71.13558000599839]
  We study the problem of solving strongly convex and smooth unconstrained optimization problems using first-order algorithms. We devise a novel, referred to as Recursive One-Over-T SGD, based on an easily implementable, averaging of past gradients. We prove that it simultaneously achieves state-of-the-art performance in both a finite-sample, nonasymptotic sense and an sense.
  arXiv  Detail & Related papers  (2020-08-28T14:46:56Z)
• Non-asymptotic Convergence Analysis of Two Time-scale (Natural) Actor-Critic Algorithms [58.57004511121862]
  Actor-critic (AC) and natural actor-critic (NAC) algorithms are often executed in two ways for finding optimal policies. We show that two time-scale AC requires the overall sample complexity at the order of $mathcalO(epsilon-2.5log3(epsilon-1))$ to attain an $epsilon$-accurate stationary point. We develop novel techniques for bounding the bias error of the actor due to dynamically changing Markovian sampling.
  arXiv  Detail & Related papers  (2020-05-07T15:42:31Z)
• A Finite Time Analysis of Two Time-Scale Actor Critic Methods [87.69128666220016]
  We provide a non-asymptotic analysis for two time-scale actor-critic methods under non-i.i.d. setting. We prove that the actor-critic method is guaranteed to find a first-order stationary point. This is the first work providing finite-time analysis and sample complexity bound for two time-scale actor-critic methods.
  arXiv  Detail & Related papers  (2020-05-04T09:45:18Z)
• Is Temporal Difference Learning Optimal? An Instance-Dependent Analysis [102.29671176698373]
  We address the problem of policy evaluation in discounted decision processes, and provide Markov-dependent guarantees on the $ell_infty$error under a generative model. We establish both and non-asymptotic versions of local minimax lower bounds for policy evaluation, thereby providing an instance-dependent baseline by which to compare algorithms.
  arXiv  Detail & Related papers  (2020-03-16T17:15:28Z)

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.