Toward Evaluating Robustness of Deep Reinforcement Learning with Continuous Control
Deep reinforcement learning has achieved great success in many previously difficult reinforcement learning tasks, yet recent studies show that deep RL agents are also unavoidably susceptible to adversarial perturbations, similar to deep neural networks in classification tasks. Prior works mostly focus on model-free adversarial attacks and agents with discrete actions. In this work, we study the problem of continuous control agents in deep RL with adversarial attacks and propose the first two-step algorithm based on learned model dynamics. Extensive experiments on various MuJoCo domains (Cartpole, Fish, Walker, Humanoid) demonstrate that our proposed framework is much more effective and efficient than model-free based attacks baselines in degrading agent performance as well as driving agents to unsafe states.
Code (0)
등록된 구현이 없습니다.
Tasks
continuous-controlContinuous ControlDeep Reinforcement LearningMuJoCoreinforcement-learningReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Evaluating Robustness of Cooperative MARL
In recent years, a proliferation of methods were developed for multi-agent reinforcement learning (MARL). In this paper, we focus on evaluating the robustness of MARL agents in continuous control tasks. In particular, we…
continuous-controlContinuous ControlMuJoCoMulti-agent Reinforcement Learning+2Controlgym: Large-Scale Control Environments for Benchmarking Reinforcement Learning Algorithms
We introduce controlgym, a library of thirty-six industrial control settings, and ten infinite-dimensional partial differential equation (PDE)-based control problems. Integrated within the OpenAI Gym/Gymnasium (Gym) fram…
BenchmarkingOpenAI Gymreinforcement-learningReinforcement Learning+1Explicit Lipschitz Value Estimation Enhances Policy Robustness Against Perturbation
In robotic control tasks, policies trained by reinforcement learning (RL) in simulation often experience a performance drop when deployed on physical hardware, due to modeling error, measurement error, and unpredictable …
continuous-controlContinuous ControlReinforcement Learning (RL)Robust Reinforcement Learning for Continuous Control with Model Misspecification
We provide a framework for incorporating robustness -- to perturbations in the transition dynamics which we refer to as model misspecification -- into continuous control Reinforcement Learning (RL) algorithms. We specifi…
continuous-controlContinuous ControlMuJoCoreinforcement-learning+2Ctrl-Z: Recovering from Instability in Reinforcement Learning
When learning behavior, training data is often generated by the learner itself; this can result in unstable training dynamics, and this problem has particularly important applications in safety-sensitive real-world contr…
continuous-controlContinuous Controlreinforcement-learningReinforcement Learning+2