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 11–20 of 135 papers

TitleStatusHype
Neurosymbolic Reinforcement Learning with Formally Verified ExplorationCode1
Autonomous UAV Exploration of Dynamic Environments via Incremental Sampling and Probabilistic RoadmapCode1
Toward Safe and Accelerated Deep Reinforcement Learning for Next-Generation Wireless NetworksCode1
Model-based Safe Deep Reinforcement Learning via a Constrained Proximal Policy Optimization AlgorithmCode1
Align-RUDDER: Learning From Few Demonstrations by Reward RedistributionCode1
Bayesian Controller Fusion: Leveraging Control Priors in Deep Reinforcement Learning for Robotics—0
Avoiding Negative Side-Effects and Promoting Safe Exploration with Imaginative Planning—0
Ablation Study of How Run Time Assurance Impacts the Training and Performance of Reinforcement Learning Agents—0
A Human-Centered Safe Robot Reinforcement Learning Framework with Interactive Behaviors—0
Conservative Safety Critics for Exploration—0
Show:102550
← PrevPage 2 of 14Next →

No leaderboard results yet.