Probabilistically safe and efficient model-based Reinforcement Learning
This paper proposes tackling safety-critical stochastic Reinforcement Learning (RL) tasks with a samplebased, model-based approach. At the core of the method lies a Model Predictive Control (MPC) scheme that acts as function approximation, providing a model-based predictive control policy. To ensure safety, a probabilistic Control Barrier Function (CBF) is integrated into the MPC controller. A sample-based approach with guarantees is employed to approximate the effects of stochasticies in the optimal control formulation and to guarantee the probabilistic CBF condition. A learnable terminal cost formulation is included in the MPC objective to counterbalance the additional computational burden due to sampling. An RL algorithm is deployed to learn both the terminal cost and the CBF constraint. Results from our numerical experiment on a constrained LTI problem corroborate the effectiveness of the proposed methodology in reducing computation time while preserving control performance and safety.
Code (1)
Tasks
Model-based Reinforcement LearningModel Predictive Controlreinforcement-learningReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Kernel-Based Safe Exploration in Deep Reinforcement Learning
Safety has been a major concern when deploying deep reinforcement learning algorithms in the real world. A promising direction that ensures that the learned policy does not visit unsafe regions is to learn a \emph{barrie…
Reinforcement LearningContinuous ControlSim-to-Lab-to-Real: Safe Reinforcement Learning with Shielding and Generalization Guarantees
Safety is a critical component of autonomous systems and remains a challenge for learning-based policies to be utilized in the real world. In particular, policies learned using reinforcement learning often fail to genera…
reinforcement-learningReinforcement Learning (RL)Safe Reinforcement LearningLearning diverse attacks on large language models for robust red-teaming and safety tuning
Red-teaming, or identifying prompts that elicit harmful responses, is a critical step in ensuring the safe and responsible deployment of large language models (LLMs). Developing effective protection against many modes of…
DiversityLanguage ModelingLanguage ModellingRed TeamingMeta-active Learning in Probabilistically-Safe Optimization
Learning to control a safety-critical system with latent dynamics (e.g. for deep brain stimulation) requires taking calculated risks to gain information as efficiently as possible. To address this problem, we present a p…
Active LearningMeta-LearningProbabilistically-Safe Bipedal Navigation over Uncertain Terrain via Conformal Prediction and Contraction Analysis
We address the challenge of enabling bipedal robots to traverse rough terrain by developing probabilistically safe planning and control strategies that ensure dynamic feasibility and centroidal robustness under terrain u…