Primal-Dual Policy Optimization for Linear CMDPs with Adversarial Losses

• URL: http://arxiv.org/abs/2605.11535v1
• Date: Tue, 12 May 2026 05:02:02 GMT
• Title: Primal-Dual Policy Optimization for Linear CMDPs with Adversarial Losses
• Abstract summary: We introduce and run with a new class of policies, which we call weighted LogSumExp softmax policies.<n>Two novel algorithmic components -- periodic policy mixing and a regularized dual update -- allow us to effectively control both the covering number and the dual variable.
• Score: 0.8984888893275712
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Existing work on linear constrained Markov decision processes (CMDPs) has primarily focused on stochastic settings, where the losses and costs are either fixed or drawn from fixed distributions. However, such formulations are inherently vulnerable to adversarially changing environments. To overcome this limitation, we propose a primal-dual policy optimization algorithm for online finite-horizon {adversarial} linear CMDPs, where the losses are adversarially chosen under full-information feedback and the costs are stochastic under bandit feedback. Our algorithm is the \emph{first} to achieve sublinear regret and constraint violation bounds in this setting, both bounded by $\widetilde{\mathcal{O}}(K^{3/4})$, where $K$ denotes the number of episodes. The algorithm introduces and runs with a new class of policies, which we call weighted LogSumExp softmax policies, designed to adapt to adversarially chosen loss functions. Our main result stems from the following key contributions: (i) a new covering number argument for the weighted LogSumExp softmax policies, and (ii) two novel algorithmic components -- periodic policy mixing and a regularized dual update -- which allow us to effectively control both the covering number and the dual variable. We also report numerical results that validate our theoretical findings on the performance of the algorithm.

Related papers

• Near-Optimal Primal-Dual Algorithm for Learning Linear Mixture CMDPs with Adversarial Rewards [0.8984888893275712]
  We study safe reinforcement learning in finite-horizon linear mixture constrained Markov decision processes.<n>We propose a primal-dual policy optimization algorithm that achieves regret and constraint violation bounds.<n>This is the first provably efficient algorithm for linear mixture CMDPs with adversarial rewards.
  arXiv  Detail & Related papers  (2026-03-29T21:51:33Z)
• Near-Optimal Dynamic Regret for Adversarial Linear Mixture MDPs [63.47351876442425]
  We study episodic linear mixture MDPs with the unknown transition and adversarial rewards under full-information feedback. We propose a novel algorithm that combines the benefits of two popular methods: occupancy-measure-based and policy-based. Our algorithm enjoys an $widetildemathcalO(d sqrtH3 K + sqrtHK(H + barP_K$)$ dynamic regret, where $d$ is the feature dimension.
  arXiv  Detail & Related papers  (2024-11-05T13:55:52Z)
• Optimal Strong Regret and Violation in Constrained MDPs via Policy Optimization [37.24692425018]
  We study online learning in emphconstrained MDPs (CMDPs) Our algorithm implements a primal-dual scheme that employs a state-of-the-art policy optimization approach for adversarial MDPs.
  arXiv  Detail & Related papers  (2024-10-03T07:54:04Z)
• Best-of-Both-Worlds Policy Optimization for CMDPs with Bandit Feedback [34.7178680288326]
  Stradi et al.(2024) proposed the first best-of-both-worlds algorithm for constrained Markov decision processes.<n>In this paper, we provide the first best-of-both-worlds algorithm for CMDPs with bandit feedback.<n>Our algorithm is based on a policy optimization approach, which is much more efficient than occupancy-measure-based methods.
  arXiv  Detail & Related papers  (2024-10-03T07:44:40Z)
• Learning General Parameterized Policies for Infinite Horizon Average Reward Constrained MDPs via Primal-Dual Policy Gradient Algorithm [34.593772931446125]
  We propose a primal dual-based policy gradient algorithm that adeptly manages the constraints while ensuring a low regret guarantee toward achieving a global optimal policy. Our proposed algorithm achieves $tildemathcalO(T4/5)$ objective regret and $tildemathcalO(T4/5)$ constraint violation bounds.
  arXiv  Detail & Related papers  (2024-02-03T05:35:58Z)
• Model-Free, Regret-Optimal Best Policy Identification in Online CMDPs [17.62509045102346]
  This paper considers the best policy identification problem in online Constrained Markov Decision Processes (CMDPs) We are interested in algorithms that are model-free, have low regret, and identify an approximately optimal policy with a high probability. Existing model-free algorithms for online CMDPs with sublinear regret and constraint violation do not provide any convergence guarantee to an optimal policy.
  arXiv  Detail & Related papers  (2023-09-27T04:33:09Z)
• 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)
• Efficient Policy Iteration for Robust Markov Decision Processes via Regularization [49.05403412954533]
  Robust decision processes (MDPs) provide a framework to model decision problems where the system dynamics are changing or only partially known. Recent work established the equivalence between texttts rectangular $L_p$ robust MDPs and regularized MDPs, and derived a regularized policy iteration scheme that enjoys the same level of efficiency as standard MDPs. In this work, we focus on the policy improvement step and derive concrete forms for the greedy policy and the optimal robust Bellman operators.
  arXiv  Detail & Related papers  (2022-05-28T04:05:20Z)
• Optimistic Policy Optimization is Provably Efficient in Non-stationary MDPs [113.8752163061151]
  We study episodic reinforcement learning (RL) in non-stationary linear kernel Markov decision processes (MDPs)<n>We propose the underlineperiodically underlinerestarted underlineoptimistic underlinepolicy underlineoptimization algorithm (PROPO)<n>PROPO features two mechanisms: sliding-window-based policy evaluation and periodic-restart-based policy improvement.
  arXiv  Detail & Related papers  (2021-10-18T02:33:20Z)
• Softmax Policy Gradient Methods Can Take Exponential Time to Converge [60.98700344526674]
  The softmax policy gradient (PG) method is arguably one of the de facto implementations of policy optimization in modern reinforcement learning. We demonstrate that softmax PG methods can take exponential time -- in terms of $mathcalS|$ and $frac11-gamma$ -- to converge.
  arXiv  Detail & Related papers  (2021-02-22T18:56:26Z)
• Provably Efficient Safe Exploration via Primal-Dual Policy Optimization [105.7510838453122]
  We study the Safe Reinforcement Learning (SRL) problem using the Constrained Markov Decision Process (CMDP) formulation. We present an provably efficient online policy optimization algorithm for CMDP with safe exploration in the function approximation setting.
  arXiv  Detail & Related papers  (2020-03-01T17:47:03Z)

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.