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 1–10 of 135 papers

TitleStatusHype
ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency PolicyCode3
MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement LearningCode2
Provably Safe PAC-MDP Exploration Using AnalogiesCode1
Feasible Actor-Critic: Constrained Reinforcement Learning for Ensuring Statewise SafetyCode1
Near-Optimal Multi-Agent Learning for Safe Coverage ControlCode1
Neurosymbolic Reinforcement Learning with Formally Verified ExplorationCode1
Autonomous UAV Exploration of Dynamic Environments via Incremental Sampling and Probabilistic RoadmapCode1
Align-RUDDER: Learning From Few Demonstrations by Reward RedistributionCode1
Model-based Safe Deep Reinforcement Learning via a Constrained Proximal Policy Optimization AlgorithmCode1
Safe Exploration in Continuous Action SpacesCode1
Show:102550
← PrevPage 1 of 14Next →

No leaderboard results yet.