Safe Reinforcement Learning With Dual Robustness

Abstract

Reinforcement learning (RL) agents are vulnerable to adversarial disturbances, which can deteriorate task performance or compromise safety specifications. Existing methods either address safety requirements under the assumption of no adversary (e.g., safe RL) or only focus on robustness against performance adversaries (e.g., robust RL). Learning one policy that is both safe and robust remains a challenging open problem. The difficulty is how to tackle two intertwined aspects in the worst cases: feasibility and optimality. Optimality is only valid inside a feasible region, while identification of maximal feasible region must rely on learning the optimal policy. To address this issue, we propose a systematic framework to unify safe RL and robust RL, including problem formulation, iteration scheme, convergence analysis and practical algorithm design. This unification is built upon constrained two-player zero-sum Markov games. A dual policy iteration scheme is proposed, which simultaneousl

Stats

• citations13
• S2 citations—
• github stars0
• HF likes0
• heat score8.60
• arxiv keyli2023safe

Related papers

• On The Robustness Of Safe Reinforcement Learning Under Observational Perturbations (2022)0.00
• Safety Correction From Baseline: Towards The Risk-aware Policy In Robotics Via Dual-agent Reinforcement Learning (2022)3.58
• Robust Model-based Reinforcement Learning With An Adversarial Auxiliary Model (2024)0.00
• Feasible Adversarial Robust Reinforcement Learning For Underspecified Environments (2022)0.00
• Robust Adversarial Policy Optimization Under Dynamics Uncertainty (2026)0.00
• Certifying Safety In Reinforcement Learning Under Adversarial Perturbation Attacks (2022)0.00
• Robust Reinforcement Learning On State Observations With Learned Optimal Adversary (2021)0.00
• Attacking And Defending Deep Reinforcement Learning Policies (2022)0.00