Adversary Agnostic Robust Deep Reinforcement Learning

Abstract

Deep reinforcement learning (DRL) policies have been shown to be deceived by perturbations (e.g., random noise or intensional adversarial attacks) on state observations that appear at test time but are unknown during training. To increase the robustness of DRL policies, previous approaches assume that the knowledge of adversaries can be added into the training process to achieve the corresponding generalization ability on these perturbed observations. However, such an assumption not only makes the robustness improvement more expensive but may also leave a model less effective to other kinds of attacks in the wild. In contrast, we propose an adversary agnostic robust DRL paradigm that does not require learning from adversaries. To this end, we first theoretically derive that robustness could indeed be achieved independently of the adversaries based on a policy distillation setting. Motivated by this finding, we propose a new policy distillation loss with two terms: 1) a prescription gap

Stats

• citations7
• S2 citations—
• github stars0
• HF likes0
• heat score6.77
• arxiv keyqu2020adversary

Related papers

• Robust Reinforcement Learning On State Observations With Learned Optimal Adversary (2021)0.00
• Robust Deep Reinforcement Learning Against Adversarial Perturbations On State Observations (2020)0.00
• Regret-based Defense In Adversarial Reinforcement Learning (2023)0.00
• Attacking And Defending Deep Reinforcement Learning Policies (2022)0.00
• Online Robust Policy Learning In The Presence Of Unknown Adversaries (2018)0.00
• Policy Smoothing For Provably Robust Reinforcement Learning (2021)0.00
• Rethinking Adversarial Attacks In Reinforcement Learning From Policy Distribution Perspective (2025)5.84
• Robust Adversarial Policy Optimization Under Dynamics Uncertainty (2026)0.00