Robust Reinforcement Learning Via Adversarial Training With Langevin Dynamics

Abstract

We introduce a sampling perspective to tackle the challenging task of training robust Reinforcement Learning (RL) agents. Leveraging the powerful Stochastic Gradient Langevin Dynamics, we present a novel, scalable two-player RL algorithm, which is a sampling variant of the two-player policy gradient method. Our algorithm consistently outperforms existing baselines, in terms of generalization across different training and testing conditions, on several MuJoCo environments. Our experiments also show that, even for objective functions that entirely ignore potential environmental shifts, our sampling approach remains highly robust in comparison to standard RL algorithms.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keykamalaruban2020robust

Related papers

• Robust Adversarial Policy Optimization Under Dynamics Uncertainty (2026)0.00
• Robust Reinforcement Learning On State Observations With Learned Optimal Adversary (2021)0.00
• Robust Model-based Reinforcement Learning With An Adversarial Auxiliary Model (2024)0.00
• Robust Deep Reinforcement Learning With Adaptive Adversarial Perturbations In Action Space (2024)6.20
• Robust Deep Reinforcement Learning Through Adversarial Loss (2020)0.00
• Sample-efficient Robust Multi-agent Reinforcement Learning In The Face Of Environmental Uncertainty (2024)0.00
• Direct Soft-policy Sampling Via Langevin Dynamics (2026)0.00
• Robust On-policy Sampling For Data-efficient Policy Evaluation In Reinforcement Learning (2021)0.00