On exploration requirements for learning safety constraints
Enforcing safety for dynamical systems is challenging, since it requires constraint satisfaction along trajectory predictions. Equivalent control constraints can be computed in the form of sets that enforce positive invariance, and can thus guarantee safety in feedback controllers without predictions. However, these constraints are cumbersome to compute from models, and it is not yet well established how to infer constraints from data. In this paper, we shed light on the key objects involved in learning control constraints from data in a model-free setting. In particular, we discuss the family of constraints that enforce safety in the context of a nominal control policy, and expose that these constraints do not need to be accurate everywhere. They only need to correctly exclude a subset of the state-actions that would cause failure, which we call the critical set.
Code (1)
Similar Papers 제목 키워드 기반
DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning
Safe reinforcement learning is extremely challenging--not only must the agent explore an unknown environment, it must do so while ensuring no safety constraint violations. We formulate this safe reinforcement learning (R…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Safe Exploration+1Safe and Adaptive Decision-Making for Optimization of Safety-Critical Systems: The ARTEO Algorithm
We consider the problem of decision-making under uncertainty in an environment with safety constraints. Many business and industrial applications rely on real-time optimization to improve key performance indicators. In t…
Decision MakingDecision Making Under UncertaintyGaussian ProcessesMulti-Armed BanditsEfficiently Computable Safety Bounds for Gaussian Processes in Active Learning
Active learning of physical systems must commonly respect practical safety constraints, which restricts the exploration of the design space. Gaussian Processes (GPs) and their calibrated uncertainty estimations are widel…
Active LearningGaussian ProcessesHandling Long-Term Safety and Uncertainty in Safe Reinforcement Learning
Safety is one of the key issues preventing the deployment of reinforcement learning techniques in real-world robots. While most approaches in the Safe Reinforcement Learning area do not require prior knowledge of constra…
reinforcement-learningReinforcement LearningSafe ExplorationSafe Reinforcement LearningConstrained Exploration and Recovery from Experience Shaping
We consider the problem of reinforcement learning under safety requirements, in which an agent is trained to complete a given task, typically formalized as the maximization of a reward signal over time, while concurrentl…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)