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

Showing 2130 of 135 papers

TitleStatusHype
DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement LearningCode0
Confidence-Guided Human-AI Collaboration: Reinforcement Learning with Distributional Proxy Value Propagation for Autonomous DrivingCode0
Information-Theoretic Safe Exploration with Gaussian ProcessesCode0
Concrete Problems in AI SafetyCode0
Handling Long-Term Safety and Uncertainty in Safe Reinforcement LearningCode0
Curiosity Killed or Incapacitated the Cat and the Asymptotically Optimal AgentCode0
AI Safety GridworldsCode0
Infinite Time Horizon Safety of Bayesian Neural NetworksCode0
Learning-based Model Predictive Control for Safe ExplorationCode0
Effects of Safety State Augmentation on Safe ExplorationCode0
Show:102550
← PrevPage 3 of 14Next →

No leaderboard results yet.