A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guarantees

• URL: http://arxiv.org/abs/2401.17780v3
• Date: Mon, 1 Jul 2024 12:08:25 GMT
• Title: A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guarantees
• Authors: Toshinori Kitamura, Tadashi Kozuno, Masahiro Kato, Yuki Ichihara, Soichiro Nishimori, Akiyoshi Sannai, Sho Sonoda, Wataru Kumagai, Yutaka Matsuo,
• Abstract summary: We study a primal-dual (PD) reinforcement learning (RL) algorithm for online Markov constrained decision processes (CMDPs) In this paper, we introduce a novel policy gradient PD algorithm with uniform probably approximate correctness (Uniform-PAC) guarantees, simultaneously ensuring convergence to optimal policies, sublinear regret, and sample complexity for any target accuracy. Notably, this represents the first Uniform-PAC algorithm for the online CMDP problem.
• Score: 28.974797385513263
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study a primal-dual (PD) reinforcement learning (RL) algorithm for online constrained Markov decision processes (CMDPs). Despite its widespread practical use, the existing theoretical literature on PD-RL algorithms for this problem only provides sublinear regret guarantees and fails to ensure convergence to optimal policies. In this paper, we introduce a novel policy gradient PD algorithm with uniform probably approximate correctness (Uniform-PAC) guarantees, simultaneously ensuring convergence to optimal policies, sublinear regret, and polynomial sample complexity for any target accuracy. Notably, this represents the first Uniform-PAC algorithm for the online CMDP problem. In addition to the theoretical guarantees, we empirically demonstrate in a simple CMDP that our algorithm converges to optimal policies, while baseline algorithms exhibit oscillatory performance and constraint violation.

Related papers

• Truly No-Regret Learning in Constrained MDPs [61.78619476991494]
  We propose a model-based primal-dual algorithm to learn in an unknown CMDP. We prove that our algorithm achieves sublinear regret without error cancellations.
  arXiv  Detail & Related papers  (2024-02-24T09:47:46Z)
• Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs [107.28031292946774]
  We study the problem of computing an optimal policy of an infinite-horizon discounted Markov decision process (constrained MDP) We develop two single-time-scale policy-based primal-dual algorithms with non-asymptotic convergence of their policy iterates to an optimal constrained policy. To the best of our knowledge, this work appears to be the first non-asymptotic policy last-iterate convergence result for single-time-scale algorithms in constrained MDPs.
  arXiv  Detail & Related papers  (2023-06-20T17:27:31Z)
• Iteratively Refined Behavior Regularization for Offline Reinforcement Learning [57.10922880400715]
  In this paper, we propose a new algorithm that substantially enhances behavior-regularization based on conservative policy iteration. By iteratively refining the reference policy used for behavior regularization, conservative policy update guarantees gradually improvement. Experimental results on the D4RL benchmark indicate that our method outperforms previous state-of-the-art baselines in most tasks.
  arXiv  Detail & Related papers  (2023-06-09T07:46:24Z)
• ACPO: A Policy Optimization Algorithm for Average MDPs with Constraints [36.16736392624796]
  We introduce a new policy optimization with function approximation algorithm for constrained MDPs with the average criterion. We develop basic sensitivity theory for average CMDPs, and then use the corresponding bounds in the design of the algorithm. We show its superior empirical performance when compared to other state-of-the-art algorithms adapted for the ACMDPs.
  arXiv  Detail & Related papers  (2023-02-02T00:23:36Z)
• Offline Policy Optimization in RL with Variance Regularizaton [142.87345258222942]
  We propose variance regularization for offline RL algorithms, using stationary distribution corrections. We show that by using Fenchel duality, we can avoid double sampling issues for computing the gradient of the variance regularizer. The proposed algorithm for offline variance regularization (OVAR) can be used to augment any existing offline policy optimization algorithms.
  arXiv  Detail & Related papers  (2022-12-29T18:25:01Z)
• Making Linear MDPs Practical via Contrastive Representation Learning [101.75885788118131]
  It is common to address the curse of dimensionality in Markov decision processes (MDPs) by exploiting low-rank representations. We consider an alternative definition of linear MDPs that automatically ensures normalization while allowing efficient representation learning. We demonstrate superior performance over existing state-of-the-art model-based and model-free algorithms on several benchmarks.
  arXiv  Detail & Related papers  (2022-07-14T18:18:02Z)
• A Policy Efficient Reduction Approach to Convex Constrained Deep Reinforcement Learning [2.811714058940267]
  We propose a new variant of the conditional gradient (CG) type algorithm, which generalizes the minimum norm point (MNP) method. Our method reduces the memory costs by an order of magnitude, and achieves better performance, demonstrating both its effectiveness and efficiency.
  arXiv  Detail & Related papers  (2021-08-29T20:51:32Z)
• Uniform-PAC Bounds for Reinforcement Learning with Linear Function Approximation [92.3161051419884]
  We study reinforcement learning with linear function approximation. Existing algorithms only have high-probability regret and/or Probably Approximately Correct (PAC) sample complexity guarantees. We propose a new algorithm called FLUTE, which enjoys uniform-PAC convergence to the optimal policy with high probability.
  arXiv  Detail & Related papers  (2021-06-22T08:48:56Z)
• Fast Global Convergence of Natural Policy Gradient Methods with Entropy Regularization [44.24881971917951]
  Natural policy gradient (NPG) methods are among the most widely used policy optimization algorithms. We develop convergence guarantees for entropy-regularized NPG methods under softmax parameterization. Our results accommodate a wide range of learning rates, and shed light upon the role of entropy regularization in enabling fast convergence.
  arXiv  Detail & Related papers  (2020-07-13T17:58:41Z)
• Robust Reinforcement Learning using Least Squares Policy Iteration with Provable Performance Guarantees [3.8073142980733]
  This paper addresses the problem of model-free reinforcement learning for Robust Markov Decision Process (RMDP) with large state spaces. We first propose the Robust Least Squares Policy Evaluation algorithm, which is a multi-step online model-free learning algorithm for policy evaluation. We then propose Robust Least Squares Policy Iteration (RLSPI) algorithm for learning the optimal robust policy.
  arXiv  Detail & Related papers  (2020-06-20T16:26:50Z)

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.