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 41–50 of 135 papers

TitleStatusHype
Handling Long-Term Safety and Uncertainty in Safe Reinforcement LearningCode0
Concrete Problems in AI SafetyCode0
GoSafeOpt: Scalable Safe Exploration for Global Optimization of Dynamical SystemsCode0
DESTA: A Framework for Safe Reinforcement Learning with Markov Games of Intervention—0
Decoupled Learning of Environment Characteristics for Safe Exploration—0
Bayesian Controller Fusion: Leveraging Control Priors in Deep Reinforcement Learning for Robotics—0
Data-efficient visuomotor policy training using reinforcement learning and generative models—0
Data Efficient Reinforcement Learning for Legged Robots—0
Avoiding Negative Side-Effects and Promoting Safe Exploration with Imaginative Planning—0
Learning-based Symbolic Abstractions for Nonlinear Control Systems—0
Show:102550
← PrevPage 5 of 14Next →

No leaderboard results yet.