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 26–50 of 135 papers

TitleStatusHype
Learning to Control Highly Accelerated Ballistic Movements on Muscular Robots—0
Data Efficient Reinforcement Learning for Legged Robots—0
Data-efficient visuomotor policy training using reinforcement learning and generative models—0
Decoupled Learning of Environment Characteristics for Safe Exploration—0
DESTA: A Framework for Safe Reinforcement Learning with Markov Games of Intervention—0
Learning to explore when mistakes are not allowed—0
ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning—0
Chance-Constrained Trajectory Optimization for Safe Exploration and Learning of Nonlinear Systems—0
Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPs—0
Learning Transferable Domain Priors for Safe Exploration in Reinforcement Learning—0
Building HVAC Scheduling Using Reinforcement Learning via Neural Network Based Model Approximation—0
Exploration of Unranked Items in Safe Online Learning to Re-Rank—0
Approximate Shielding of Atari Agents for Safe Exploration—0
Exploration in Deep Reinforcement Learning: A Survey—0
Guiding Safe Exploration with Weakest Preconditions—0
A Safe Self-evolution Algorithm for Autonomous Driving Based on Data-Driven Risk Quantification Model—0
Highway Value Iteration Networks—0
A Safe Semi-supervised Graph Convolution Network—0
Information-Theoretic Safe Bayesian Optimization—0
Effects of Safety State Augmentation on Safe Exploration—0
A safe exploration approach to constrained Markov decision processes—0
Conservative Safety Critics for Exploration—0
A Human-Centered Safe Robot Reinforcement Learning Framework with Interactive Behaviors—0
Learning-based Symbolic Abstractions for Nonlinear Control Systems—0
BubbleRank: Safe Online Learning to Re-Rank via Implicit Click Feedback—0
Show:102550
← PrevPage 2 of 6Next →

No leaderboard results yet.