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 51–75 of 135 papers

TitleStatusHype
Near-Optimal Multi-Agent Learning for Safe Coverage ControlCode1
Safe Exploration Method for Reinforcement Learning under Existence of DisturbanceCode0
Guiding Safe Exploration with Weakest Preconditions—0
Safe Reinforcement Learning of Dynamic High-Dimensional Robotic Tasks: Navigation, Manipulation, Interaction—0
Toward Safe and Accelerated Deep Reinforcement Learning for Next-Generation Wireless NetworksCode1
Safe Reinforcement Learning with Contrastive Risk Prediction—0
Recursively Feasible Probabilistic Safe Online Learning with Control Barrier Functions—0
Sample-efficient Safe Learning for Online Nonlinear Control with Control Barrier Functions—0
Ablation Study of How Run Time Assurance Impacts the Training and Performance of Reinforcement Learning Agents—0
A Safe Semi-supervised Graph Convolution Network—0
Safe Exploration Incurs Nearly No Additional Sample Complexity for Reward-free RL—0
Effects of Safety State Augmentation on Safe ExplorationCode0
Learning to Drive Using Sparse Imitation Reinforcement Learning—0
Learn-to-Race Challenge 2022: Benchmarking Safe Learning and Cross-domain Generalisation in Autonomous Racing—0
Exploration in Deep Reinforcement Learning: A Survey—0
SCOPE: Safe Exploration for Dynamic Computer Systems Optimization—0
SAAC: Safe Reinforcement Learning as an Adversarial Game of Actor-Critics—0
Training and Evaluation of Deep Policies using Reinforcement Learning and Generative Models—0
Safe Reinforcement Learning via Shielding under Partial Observability—0
Safe Exploration for Efficient Policy Evaluation and Comparison—0
CUP: A Conservative Update Policy Algorithm for Safe Reinforcement LearningCode0
Model-Based Offline Meta-Reinforcement Learning with Regularization—0
Provably Efficient Primal-Dual Reinforcement Learning for CMDPs with Non-stationary Objectives and Constraints—0
GoSafeOpt: Scalable Safe Exploration for Global Optimization of Dynamical SystemsCode0
MESA: Offline Meta-RL for Safe Adaptation and Fault Tolerance—0
Show:102550
← PrevPage 3 of 6Next →

No leaderboard results yet.