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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 51–100 of 135 papers

Title	Date	Tasks	Status	Hype
Near-Optimal Multi-Agent Learning for Safe Coverage Control	Oct 12, 2022	DiversityNavigate	CodeCode Available	1
Safe Exploration Method for Reinforcement Learning under Existence of Disturbance	Sep 30, 2022	reinforcement-learningReinforcement Learning	CodeCode Available	0
Guiding Safe Exploration with Weakest Preconditions	Sep 28, 2022	continuous-controlContinuous Control	—Unverified	0
Safe Reinforcement Learning of Dynamic High-Dimensional Robotic Tasks: Navigation, Manipulation, Interaction	Sep 27, 2022	reinforcement-learningReinforcement Learning	—Unverified	0
Toward Safe and Accelerated Deep Reinforcement Learning for Next-Generation Wireless Networks	Sep 16, 2022	Deep Reinforcement LearningManagement	CodeCode Available	1
Safe Reinforcement Learning with Contrastive Risk Prediction	Sep 10, 2022	Predictionreinforcement-learning	—Unverified	0
Recursively Feasible Probabilistic Safe Online Learning with Control Barrier Functions	Aug 23, 2022	Out-of-Distribution DetectionSafe Exploration	—Unverified	0
Sample-efficient Safe Learning for Online Nonlinear Control with Control Barrier Functions	Jul 29, 2022	Decision MakingReinforcement Learning (RL)	—Unverified	0
Ablation Study of How Run Time Assurance Impacts the Training and Performance of Reinforcement Learning Agents	Jul 8, 2022	reinforcement-learningReinforcement Learning	—Unverified	0
A Safe Semi-supervised Graph Convolution Network	Jul 5, 2022	Safe Exploration	—Unverified	0
Safe Exploration Incurs Nearly No Additional Sample Complexity for Reward-free RL	Jun 28, 2022	Safe Exploration	—Unverified	0
Effects of Safety State Augmentation on Safe Exploration	Jun 6, 2022	Reinforcement Learning (RL)Safe Exploration	CodeCode Available	0
Learning to Drive Using Sparse Imitation Reinforcement Learning	May 24, 2022	Autonomous Drivingreinforcement-learning	—Unverified	0
Learn-to-Race Challenge 2022: Benchmarking Safe Learning and Cross-domain Generalisation in Autonomous Racing	May 5, 2022	Autonomous DrivingAutonomous Racing	—Unverified	0
Exploration in Deep Reinforcement Learning: A Survey	May 2, 2022	Deep Reinforcement Learningreinforcement-learning	—Unverified	0
SCOPE: Safe Exploration for Dynamic Computer Systems Optimization	Apr 22, 2022	Safe Exploration	—Unverified	0
SAAC: Safe Reinforcement Learning as an Adversarial Game of Actor-Critics	Apr 20, 2022	continuous-controlContinuous Control	—Unverified	0
Training and Evaluation of Deep Policies using Reinforcement Learning and Generative Models	Apr 18, 2022	Decision Makingreinforcement-learning	—Unverified	0
Safe Reinforcement Learning via Shielding under Partial Observability	Apr 2, 2022	reinforcement-learningReinforcement Learning	—Unverified	0
Safe Exploration for Efficient Policy Evaluation and Comparison	Feb 26, 2022	Safe Exploration	—Unverified	0
CUP: A Conservative Update Policy Algorithm for Safe Reinforcement Learning	Feb 15, 2022	reinforcement-learningReinforcement Learning	CodeCode Available	0
Model-Based Offline Meta-Reinforcement Learning with Regularization	Feb 7, 2022	Meta Reinforcement Learningreinforcement-learning	—Unverified	0
Provably Efficient Primal-Dual Reinforcement Learning for CMDPs with Non-stationary Objectives and Constraints	Jan 28, 2022	Reinforcement Learning (RL)Safe Exploration	—Unverified	0
GoSafeOpt: Scalable Safe Exploration for Global Optimization of Dynamical Systems	Jan 24, 2022	global-optimizationSafe Exploration	CodeCode Available	0
MESA: Offline Meta-RL for Safe Adaptation and Fault Tolerance	Dec 7, 2021	continuous-controlContinuous Control	—Unverified	0
DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning	Dec 1, 2021	reinforcement-learningReinforcement Learning	CodeCode Available	0
Safe Policy Optimization with Local Generalized Linear Function Approximations	Nov 9, 2021	Reinforcement Learning (RL)Safe Exploration	CodeCode Available	0
Infinite Time Horizon Safety of Bayesian Neural Networks	Nov 4, 2021	reinforcement-learningReinforcement Learning	CodeCode Available	0
DESTA: A Framework for Safe Reinforcement Learning with Markov Games of Intervention	Oct 27, 2021	OpenAI Gymreinforcement-learning	—Unverified	0
Dual-Arm Adversarial Robot Learning	Oct 15, 2021	Safe Exploration	—Unverified	0
Safe Exploration in Linear Equality Constraint	Sep 29, 2021	reinforcement-learningReinforcement Learning	—Unverified	0
MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning	Sep 26, 2021	BenchmarkingDecision Making	CodeCode Available	2
Safety-Critical Learning of Robot Control with Temporal Logic Specifications	Sep 7, 2021	Gaussian ProcessesReinforcement Learning (RL)	—Unverified	0
Bayesian Controller Fusion: Leveraging Control Priors in Deep Reinforcement Learning for Robotics	Jul 21, 2021	Deep Reinforcement Learningreinforcement-learning	—Unverified	0
Safe Exploration by Solving Early Terminated MDP	Jul 9, 2021	Reinforcement Learning (RL)Safe Exploration	—Unverified	0
Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPs	Jun 4, 2021	Safe Exploration	—Unverified	0
Feasible Actor-Critic: Constrained Reinforcement Learning for Ensuring Statewise Safety	May 22, 2021	reinforcement-learningReinforcement Learning	CodeCode Available	1
Safe Exploration in Model-based Reinforcement Learning using Control Barrier Functions	Apr 16, 2021	Model-based Reinforcement Learningreinforcement-learning	—Unverified	0
Safe Continuous Control with Constrained Model-Based Policy Optimization	Apr 14, 2021	continuous-controlContinuous Control	CodeCode Available	0
Towards Safe Continuing Task Reinforcement Learning	Feb 24, 2021	reinforcement-learningReinforcement Learning	—Unverified	0
Safe model-based design of experiments using Gaussian processes	Nov 19, 2020	Experimental DesignGaussian Processes	—Unverified	0
Conservative Safety Critics for Exploration	Oct 27, 2020	Reinforcement Learning (RL)Safe Exploration	—Unverified	0
Autonomous UAV Exploration of Dynamic Environments via Incremental Sampling and Probabilistic Roadmap	Oct 14, 2020	Safe Exploration	CodeCode Available	1
Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution	Sep 29, 2020	General Reinforcement LearningMinecraft	CodeCode Available	1
Neurosymbolic Reinforcement Learning with Formally Verified Exploration	Sep 26, 2020	reinforcement-learningReinforcement Learning	CodeCode Available	1
Data-efficient visuomotor policy training using reinforcement learning and generative models	Jul 26, 2020	Decision MakingDisentanglement	—Unverified	0
Provably Safe PAC-MDP Exploration Using Analogies	Jul 7, 2020	reinforcement-learningReinforcement Learning	CodeCode Available	1
Verifiably Safe Exploration for End-to-End Reinforcement Learning	Jul 2, 2020	Deep Reinforcement Learningobject-detection	CodeCode Available	1
Enforcing Almost-Sure Reachability in POMDPs	Jun 30, 2020	Decision Makingreinforcement-learning	CodeCode Available	0
Curiosity Killed or Incapacitated the Cat and the Asymptotically Optimal Agent	Jun 5, 2020	reinforcement-learningReinforcement Learning	CodeCode Available	0

Show:10 25 50

← PrevPage 2 of 3Next →

No leaderboard results yet.