SOTAVerified

Safe Exploration

Safe Exploration is an approach to collect ground truth data by safely interacting with the environment.

Source: Chance-Constrained Trajectory Optimization for Safe Exploration and Learning of Nonlinear Systems

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 76–100 of 135 papers

TitleStatusHype
Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPs—0
Learning to Control Highly Accelerated Ballistic Movements on Muscular Robots—0
Learning to Drive Using Sparse Imitation Reinforcement Learning—0
Learning to explore when mistakes are not allowed—0
Learning Transferable Domain Priors for Safe Exploration in Reinforcement Learning—0
Learn-to-Race Challenge 2022: Benchmarking Safe Learning and Cross-domain Generalisation in Autonomous Racing—0
Linear Stochastic Bandits Under Safety Constraints—0
MESA: Offline Meta-RL for Safe Adaptation and Fault Tolerance—0
Meta SAC-Lag: Towards Deployable Safe Reinforcement Learning via MetaGradient-based Hyperparameter Tuning—0
Model-Assisted Probabilistic Safe Adaptive Control With Meta-Bayesian Learning—0
Model-Based Offline Meta-Reinforcement Learning with Regularization—0
Preparing for Black Swans: The Antifragility Imperative for Machine Learning—0
Recursively Feasible Probabilistic Safe Online Learning with Control Barrier Functions—0
Provably Efficient Primal-Dual Reinforcement Learning for CMDPs with Non-stationary Objectives and Constraints—0
Provably Efficient Safe Exploration via Primal-Dual Policy Optimization—0
Provably Learning Nash Policies in Constrained Markov Potential Games—0
Reinforcement Learning by Guided Safe Exploration—0
Revisiting Safe Exploration in Safe Reinforcement learning—0
Robust Deep Reinforcement Learning for Volt-VAR Optimization in Active Distribution System under Uncertainty—0
Robust Regression for Safe Exploration in Control—0
SAAC: Safe Reinforcement Learning as an Adversarial Game of Actor-Critics—0
Safe Bayesian Optimization for the Control of High-Dimensional Embodied Systems—0
Safety-Critical Learning of Robot Control with Temporal Logic Specifications—0
Safe deep reinforcement learning-based constrained optimal control scheme for active distribution networks—0
Safe Exploration by Solving Early Terminated MDP—0
Show:102550
← PrevPage 4 of 6Next →

No leaderboard results yet.