Scholarlink

<p>Reinforcement learning (RL) faces significant challenges when deployed in real-world scenarios with potential adversarial perturbations. The Intrinsic State-Adversarial Markov Decision Process (ISA-MDP) framework considers state perturbation to enhance policy robustness while preserving its natural performance. Building upon ISA-MDP, this paper proposes the first policy optimization framework and develops two distinct algorithms for different scenarios: Deterministic Adversarially Robust Policy Gradient (DARPG) and stochastic adversarially robust policy optimization, which effectively solve our formulated optimization problem. Furthermore, we provide a convergence analysis for both algorithms under specified theoretical assumptions.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

ARPO: Optimal Robust Policy Optimization Models from Intrinsic State-Adversarial Markov Decision Process

  • 期刊论文

  • 发表日期：

    2026年5月6日

查看全文
  • Jia-Yu Lv,
  • Hao-Ran Li,
  • Cong-Ying Han,
  • Tian-De Guo

摘要

Reinforcement learning (RL) faces significant challenges when deployed in real-world scenarios with potential adversarial perturbations. The Intrinsic State-Adversarial Markov Decision Process (ISA-MDP) framework considers state perturbation to enhance policy robustness while preserving its natural performance. Building upon ISA-MDP, this paper proposes the first policy optimization framework and develops two distinct algorithms for different scenarios: Deterministic Adversarially Robust Policy Gradient (DARPG) and stochastic adversarially robust policy optimization, which effectively solve our formulated optimization problem. Furthermore, we provide a convergence analysis for both algorithms under specified theoretical assumptions.