No article text was recorded for this version.
safe exploration
Version 2 of 22,922 papers4,411 conceptsfrozen 2026-10-04
Papers in this version
- Blog: A Review of Safe Reinforcement Learning: Methods, Theories, and Applications
- Blog: Revisiting Safe Exploration in Safe Reinforcement learning
- Blog: Active Learning with Safety Constraints
- Blog: Safe Online Bid Optimization with Return-On-Investment and Budget Constraints subject to Uncertainty
- Blog: Price of Safety in Linear Best Arm Identification
- Blog: Safe Reinforcement Learning in Constrained Markov Decision Processes
- Blog: A safe exploration approach to constrained Markov decision processes
- Blog: Conservative Contextual Combinatorial Cascading Bandit
- Blog: Linear Stochastic Bandits Under Safety Constraints
- Blog: Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark
- Blog: Contextual Bandits with Stage-wise Constraints
- Blog: A Unified Framework for Conservative Exploration
- Blog: Provably Efficient RL for Linear MDPs under Instantaneous Safety Constraints in Non-Convex Feature Spaces
- Blog: Safely Bridging Offline and Online Reinforcement Learning
- Blog: Curiosity Killed the Cat and the Asymptotically Optimal Agent
- Blog: A safe exploration approach to constrained Markov decision processes
- Blog: System III: Learning with Domain Knowledge for Safety Constraints
- Blog: Learn Zero-Constraint-Violation Policy in Model-Free Constrained Reinforcement Learning
- Blog: Safe Reinforcement Learning via Shielding under Partial Observability
- Blog: Multi-Armed Bandits with Abstention
- Blog: Safe Learning in Tree-Form Sequential Decision Making: Handling Hard and Soft Constraints
- Blog: HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agents
- Blog: Conservative Safety Critics for Exploration
- Blog: Learning Transferable Domain Priors for Safe Exploration in Reinforcement Learning
- Blog: Safe Inverse Reinforcement Learning via Control Barrier Function
- Blog: Reinforcement Learning with Adaptive Control Regularization for Safe Control of Critical Systems
- Blog: Optimistic Exploration for Risk-Averse Constrained Reinforcement Learning
- Blog: SAMBA: Safe Model-Based & Active Reinforcement Learning
- Blog: Absolute State-wise Constrained Policy Optimization: High-Probability State-wise Constraints Satisfaction
- Blog: Lyapunov Barrier Policy Optimization
- Blog: Learning to be safe, in finite time
- Blog: Safe Linear Thompson Sampling With Side Information
- Blog: SafeLight: A Reinforcement Learning Method toward Collision-free Traffic Signal Control
- Blog: Contextual Combinatorial Conservative Bandits
- Blog: Safe Reinforcement Learning with Linear Function Approximation
- Blog: Conservative Bandits
- Blog: Conservative Exploration in Reinforcement Learning
- Blog: Safe Linear Thompson Sampling
- Blog: A Review of Smart Grid Evolution and Reinforcement Learning: Applications, Challenges and Future Directions
- Blog: Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability
- Blog: Evaluation of Constrained Reinforcement Learning Algorithms for Legged Locomotion
- Blog: The Survival Bandit Problem
- Blog: Online Learning with Unknown Constraints
- Blog: Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones
- Blog: Learning Gentle Object Manipulation with Curiosity-Driven Deep Reinforcement Learning
- Blog: Safe- to-Explore State Spaces: Ensuring Safe Exploration in Policy Search with Hierarchical Task Optimization
- Blog: Modeling Risk in Reinforcement Learning: A Literature Mapping
- Blog: Better Optimism By Bayes: Adaptive Planning with Rich Models
- Blog: Conservative Exploration using Interleaving
- Blog: A Survey of Constraint Formulations in Safe Reinforcement Learning
- Blog: Do Androids Dream of Electric Fences? Safety-Aware Reinforcement Learning with Latent Shielding
- Blog: Ablation Study of How Run Time Assurance Impacts the Training and Performance of Reinforcement Learning Agents
- Blog: Towards Safe Continuing Task Reinforcement Learning
- Blog: A Practical Approach for Safe Exploration
- Blog: Curiosity Killed the Cat and the Asymptotically Optimal Agent
- Blog: A Modern Perspective on Safe Automated Driving for Different Traffic Dynamics Using Constrained Reinforcement Learning
- Blog: Vehicle Lateral Control Based on Augmented Lagrangian DDPG Algorithm
- Blog: Probabilistically safe policy transfer
- Blog: SaVeR: Optimal Data Collection Strategy for Safe Policy Evaluation in Tabular MDP
- Blog: ROBEL: Robotics Benchmarks for Learning with Low-Cost Robots
Showing 60 of 2,922 papers.
History & citation
Current · Permanent link
- Safe Exploration for Tabula Rasa Reinforcement Learning merged into this direction (70% overlap)
- Funding Exploration with a Safety Budget merged into this direction (77% overlap)
- Learning from Human Interventions to Avoid Catastrophic Failure merged into this direction (71% overlap)
- Safe Bayesian Optimization for Physical Systems merged into this direction (66% overlap)
- Learning Safety Constraints from Demonstrations and Interaction merged into this direction (57% overlap)
- Optimistic Exploration under Pessimistic Safety Constraints merged into this direction (64% overlap)
- Recursive Safety Value Functions for Hard Constraints merged into this direction (82% overlap)
- Safe Optimization via Decoupled Exploration and Exploitation merged into this direction (75% overlap)
- Safe Reinforcement Learning with Zero Training Violations merged into this direction (96% overlap)
- Safe Reinforcement Learning with Latent World Models merged into this direction (67% overlap)
- Decoupling Safety Constraints from Reward Optimization merged into this direction (57% overlap)
- Escaping Conservative Local Optima in Safe Reinforcement Learning merged into this direction (70% overlap)
- Action Shielding for Safe Reinforcement Learning merged into this direction (50% overlap)
- Formal Safety Guarantees for Partially Observable Reinforcement Learning merged into this direction (50% overlap)
- Constraint Conditioned Policy Optimization for Flexible Safety merged into this direction (50% overlap)
- Safe Exploration through Guaranteed Return Paths merged into this direction (70% overlap)
- Conservative Exploration for Constrained Reinforcement Learning merged into this direction (89% overlap)
- Shielding for Safe Reinforcement Learning merged into this direction (58% overlap)
- PID Control for Stable Constrained Reinforcement Learning merged into this direction (60% overlap)
- World Models for Predictive Safety in Reinforcement Learning merged into this direction (53% overlap)
- Safe Exploration through Probabilistic Action Portfolios merged into this direction (56% overlap)
- Safety Shields for Reinforcement Learning via Action Projection merged into this direction (67% overlap)
- Safe Optimization through Adaptive Local Smoothness merged into this direction (60% overlap)
- Accelerating Reinforcement Learning via Safety-Based Search Space Pruning merged into this direction (74% overlap)
- Safety Verification for Vision-Based Control via Latent Manifolds merged into this direction (53% overlap)
- Internalizing Safety Constraints through Intervention Penalties merged into this direction (54% overlap)
- Sample Efficient Reinforcement Learning for Real World Control merged into this direction (52% overlap)
- Hardware Safety in Real World Robot Learning merged into this direction (96% overlap)
- Gradient Manipulation for Safe Reinforcement Learning merged into this direction (60% overlap)
- Safe Exploration with Gaussian Processes merged into this direction (74% overlap)
- Safe Reinforcement Learning via Constrained Optimization merged into this direction (50% overlap)
- Decoupled Safety Layers for Modular Reinforcement Learning merged into this direction (50% overlap)
- Sample Complexity of Constrained Reinforcement Learning merged into this direction (73% overlap)
- Reinforcement Learning with Instantaneous Hard Safety Constraints merged into this direction (51% overlap)
- Recovery Mechanisms for Safe Reinforcement Learning merged into this direction (71% overlap)
- shielded reinforcement learning split from this direction (61% overlap)
- constrained exploration efficiency split from this direction (60% overlap)
- initial exploration risk split from this direction (59% overlap)
- adaptive constraint tightening split from this direction (64% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_safe_exploration_6d720889,
title = {safe exploration},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/safe-exploration/rdr_6d72088930cf44e0adb2bea6f5888c73},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 2, frozen text):
@misc{lacuna_safe_exploration_6d720889_v2,
title = {safe exploration},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/safe-exploration/rdr_6d72088930cf44e0adb2bea6f5888c73/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-20},
}