Optimal Transport Perturbations for Safe Reinforcement Learning with Robustness Guarantees
Robustness and safety are critical for the trustworthy deployment of deep reinforcement learning. Real-world decision making applications require algorithms that can guarantee robust performance and safety in the presence of general environment disturbances, while making limited assumptions on the data collection process during training. In order to accomplish this goal, we introduce a safe reinforcement learning framework that incorporates robustness through the use of an optimal transport cost uncertainty set. We provide an efficient implementation based on applying Optimal Transport Perturbations to construct worst-case virtual state transitions, which does not impact data collection during training and does not require detailed simulator access. In experiments on continuous control tasks with safety constraints, our approach demonstrates robust performance while significantly improving safety at deployment time compared to standard safe reinforcement learning.
Code (1)
Tasks
continuous-controlContinuous ControlDecision MakingDeep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Safe Reinforcement LearningSimilar Papers 제목 키워드 기반
On the Robustness of Safe Reinforcement Learning under Observational Perturbations
Safe reinforcement learning (RL) trains a policy to maximize the task reward while satisfying safety constraints. While prior works focus on the performance optimality, we find that the optimal solutions of many safe RL …
Adversarial Attackreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1Action Robust Reinforcement Learning via Optimal Adversary Aware Policy Optimization
Reinforcement Learning (RL) has achieved remarkable success in sequential decision tasks. However, recent studies have revealed the vulnerability of RL policies to different perturbations, raising concerns about their ef…
Reinforcement LearningOptimal Transport-Assisted Risk-Sensitive Q-Learning
The primary goal of reinforcement learning is to develop decision-making policies that prioritize optimal performance without considering risk or safety. In contrast, safe reinforcement learning aims to mitigate or avoid…
Decision MakingQ-Learningreinforcement-learningReinforcement Learning+1OTAD: An Optimal Transport-Induced Robust Model for Agnostic Adversarial Attack
Deep neural networks (DNNs) are vulnerable to small adversarial perturbations of the inputs, posing a significant challenge to their reliability and robustness. Empirical methods such as adversarial training can defend a…
Adversarial AttackAdversarial DefenseRisk-Averse Reinforcement Learning: An Optimal Transport Perspective on Temporal Difference Learning
The primary goal of reinforcement learning is to develop decision-making policies that prioritize optimal performance, frequently without considering risk or safety. In contrast, safe reinforcement learning seeks to redu…
Decision Makingreinforcement-learningReinforcement LearningSafe Reinforcement Learning