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 91–100 of 135 papers

TitleStatusHype
Safe model-based design of experiments using Gaussian processes—0
Conservative Safety Critics for Exploration—0
Autonomous UAV Exploration of Dynamic Environments via Incremental Sampling and Probabilistic RoadmapCode1
Align-RUDDER: Learning From Few Demonstrations by Reward RedistributionCode1
Neurosymbolic Reinforcement Learning with Formally Verified ExplorationCode1
Data-efficient visuomotor policy training using reinforcement learning and generative models—0
Provably Safe PAC-MDP Exploration Using AnalogiesCode1
Verifiably Safe Exploration for End-to-End Reinforcement LearningCode1
Enforcing Almost-Sure Reachability in POMDPsCode0
Curiosity Killed or Incapacitated the Cat and the Asymptotically Optimal AgentCode0
Show:102550
← PrevPage 10 of 14Next →

No leaderboard results yet.