{"total":80,"rows":[{"id":"2403.14508","title":"Constrained Reinforcement Learning with Smoothed Log Barrier Function","created":"2024-03-21","cited_by_count":15,"area":"deeprl"},{"id":"2503.07671","title":"Probabilistic Shielding for Safe Reinforcement Learning","created":"2025-03-09","cited_by_count":12,"area":"deeprl"},{"id":"2404.11578","title":"LTL-Constrained Policy Optimization with Cycle Experience Replay","created":"2024-04-17","cited_by_count":11,"area":"deeprl"},{"id":"2407.00304","title":"A Review of Safe Reinforcement Learning Methods for Modern Power Systems","created":"2024-06-29","cited_by_count":11,"area":"deeprl"},{"id":"2411.02957","title":"Embedding Safety into RL: A New Take on Trust Region Methods","created":"2024-11-05","cited_by_count":10,"area":"deeprl"},{"id":"2501.03562","title":"Rethinking Adversarial Attacks in Reinforcement Learning from Policy Distribution Perspective","created":"2025-01-07","cited_by_count":10,"area":"deeprl"},{"id":"2503.20613","title":"State-Aware Perturbation Optimization for Robust Deep Reinforcement Learning","created":"2025-03-26","cited_by_count":8,"area":"deeprl"},{"id":"2508.01561","title":"One Subgoal at a Time: Zero-Shot Generalization to Arbitrary Linear Temporal Logic Requirements in Multi-Task Reinforcement Learning","created":"2025-08-03","cited_by_count":8,"area":"deeprl"},{"id":"2503.20844","title":"Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attacks","created":"2025-03-26","cited_by_count":7,"area":"deeprl"},{"id":"2405.18180","title":"Safe Reinforcement Learning in Black-Box Environments via Adaptive Shielding","created":"2024-05-28","cited_by_count":6,"area":"deeprl"},{"id":"2503.08241","title":"HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agents","created":"2025-03-11","cited_by_count":6,"area":"deeprl"},{"id":"2402.15197","title":"Safety Optimized Reinforcement Learning via Multi-Objective Policy Optimization","created":"2024-02-23","cited_by_count":4,"area":"deeprl"},{"id":"2508.09128","title":"A Review On Safe Reinforcement Learning Using Lyapunov and Barrier Functions","created":"2025-08-12","cited_by_count":4,"area":"deeprl"},{"id":"2405.11718","title":"Feasibility Consistent Representation Learning for Safe Reinforcement Learning","created":"2024-05-20","cited_by_count":3,"area":"deeprl"},{"id":"2407.02231","title":"Safety-Driven Deep Reinforcement Learning Framework for Cobots: A Sim2Real Approach","created":"2024-07-02","cited_by_count":3,"area":"deeprl"},{"id":"2408.07962","title":"Meta SAC-Lag: Towards Deployable Safe Reinforcement Learning via MetaGradient-based Hyperparameter Tuning","created":"2024-08-15","cited_by_count":3,"area":"deeprl"},{"id":"2412.11138","title":"Safe Reinforcement Learning using Finite-Horizon Gradient-based Estimation","created":"2024-12-15","cited_by_count":3,"area":"deeprl"},{"id":"2504.21643","title":"Designing Control Barrier Function via Probabilistic Enumeration for Safe Reinforcement Learning Navigation","created":"2025-04-30","cited_by_count":3,"area":"deeprl"},{"id":"2506.00700","title":"Central Path Proximal Policy Optimization","created":"2025-05-31","cited_by_count":3,"area":"deeprl"},{"id":"2507.08793","title":"Optimistic Exploration for Risk-Averse Constrained Reinforcement Learning","created":"2025-07-11","cited_by_count":3,"area":"deeprl"},{"id":"2509.25582","title":"Safe In-Context Reinforcement Learning","created":"2025-09-29","cited_by_count":3,"area":"deeprl"},{"id":"2510.18082","title":"Provably Optimal Reinforcement Learning under Safety Filtering","created":"2025-10-20","cited_by_count":3,"area":"deeprl"},{"id":"2407.14516","title":"RobocupGym: A challenging continuous control benchmark in Robocup","created":"2024-07-03","cited_by_count":2,"area":"deeprl"},{"id":"2409.08511","title":"Vision-driven UAV River Following: Benchmarking with Safe Reinforcement Learning","created":"2024-09-13","cited_by_count":2,"area":"deeprl"},{"id":"2502.15922","title":"On the Design of Safe Continual RL Methods for Control of Nonlinear Systems","created":"2025-02-21","cited_by_count":2,"area":"deeprl"},{"id":"2505.17248","title":"Backdoors in DRL: Four Environments Focusing on In-distribution Triggers","created":"2025-05-22","cited_by_count":2,"area":"deeprl"},{"id":"2505.21852","title":"A Provable Approach for End-to-End Safe Reinforcement Learning","created":"2025-05-28","cited_by_count":2,"area":"deeprl"},{"id":"2506.06954","title":"Safety-Aware Reinforcement Learning for Control via Risk-Sensitive Action-Value Iteration and Quantile Regression","created":"2025-06-08","cited_by_count":2,"area":"deeprl"},{"id":"2506.11033","title":"Adaptive Shielding for Safe Reinforcement Learning under Hidden-Parameter Dynamics Shifts","created":"2025-05-20","cited_by_count":2,"area":"deeprl"},{"id":"2507.00485","title":"PNAct: Crafting Backdoor Attacks in Safe Reinforcement Learning","created":"2025-07-01","cited_by_count":2,"area":"deeprl"},{"id":"2508.01883","title":"Proactive Constrained Policy Optimization with Preemptive Penalty","created":"2025-08-03","cited_by_count":2,"area":"deeprl"},{"id":"2510.20199","title":"Risk-Averse Constrained Reinforcement Learning with Optimized Certainty Equivalents","created":"2025-10-23","cited_by_count":2,"area":"deeprl"},{"id":"2603.23889","title":"Off-Policy Safe Reinforcement Learning with Constrained Optimistic Exploration","created":"2026-03-25","cited_by_count":2,"area":"deeprl"},{"id":"2606.20376","title":"CRAX: Fast Safe Reinforcement Learning Benchmarking","created":"2026-06-18","cited_by_count":2,"area":"deeprl"},{"id":"2607.15003","title":"SMC-ES: Automated synthesis of formally verified control policies","created":"2026-07-16","cited_by_count":2,"area":"deeprl"},{"id":"2402.15893","title":"Concurrent Learning of Policy and Unknown Safety Constraints in Reinforcement Learning","created":"2024-02-24","cited_by_count":1,"area":"deeprl"},{"id":"2408.10858","title":"Centralized Reward Agent for Knowledge Sharing and Transfer in Multi-Task Reinforcement Learning","created":"2024-08-20","cited_by_count":1,"area":"deeprl"},{"id":"2409.19716","title":"Constrained Reinforcement Learning for Safe Heat Pump Control","created":"2024-09-29","cited_by_count":1,"area":"deeprl"},{"id":"2504.06386","title":"SPoRt -- Safe Policy Ratio: Certified Training and Deployment of Task Policies in Model-Free RL","created":"2025-04-08","cited_by_count":1,"area":"deeprl"},{"id":"2601.11953","title":"Controlling Underestimation Bias in Constrained Reinforcement Learning for Safe Exploration","created":"2026-01-17","cited_by_count":1,"area":"deeprl"},{"id":"2602.00587","title":"Safe Langevin Soft Actor Critic","created":"2026-01-31","cited_by_count":1,"area":"deeprl"},{"id":"2602.06445","title":"ECO: Energy-Constrained Optimization with Reinforcement Learning for Humanoid Walking","created":"2026-02-06","cited_by_count":1,"area":"deeprl"},{"id":"2605.00667","title":"Augmented Lagrangian Multiplier Network for State-wise Safety in Reinforcement Learning","created":"2026-05-01","cited_by_count":1,"area":"deeprl"},{"id":"2605.06149","title":"AdaGamma: State-Dependent Discounting for Temporal Adaptation in Reinforcement Learning","created":"2026-05-07","cited_by_count":1,"area":"deeprl"},{"id":"2605.25267","title":"Latent Q-Barrier Shielding for Safe In-Context Reinforcement Learning","created":"2026-05-24","cited_by_count":1,"area":"deeprl"},{"id":"2609.34041","title":"Vision--Language Signals in Constrained RL: Safety Gains Without Anticipation","created":"2026-09-28","cited_by_count":1,"area":"deeprl"},{"id":"2406.03912","title":"GenSafe: A Generalizable Safety Enhancer for Safe Reinforcement Learning Algorithms Based on Reduced Order Markov Decision Process Model","created":"2024-06-06","cited_by_count":0,"area":"deeprl"},{"id":"2406.14047","title":"Constrained Meta Agnostic Reinforcement Learning","created":"2024-06-20","cited_by_count":0,"area":"deeprl"},{"id":"2410.20786","title":"Adversarial Constrained Policy Optimization: Improving Constrained Reinforcement Learning by Adapting Budgets","created":"2024-10-28","cited_by_count":0,"area":"deeprl"},{"id":"2412.08920","title":"From Text to Trajectory: Exploring Complex Constraint Representation and Decomposition in Safe Reinforcement Learning","created":"2024-12-12","cited_by_count":0,"area":"deeprl"},{"id":"2504.12557","title":"TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels","created":"2025-04-17","cited_by_count":0,"area":"deeprl"},{"id":"2509.09208","title":"Incentivizing Safer Actions in Policy Optimization for Constrained Reinforcement Learning","created":"2025-09-11","cited_by_count":0,"area":"deeprl"},{"id":"2510.04555","title":"Tail-Safe Hedging: Explainable Risk-Sensitive Reinforcement Learning with a White-Box CBF--QP Safety Layer in Arbitrage-Free Markets","created":"2025-10-06","cited_by_count":0,"area":"deeprl"},{"id":"2510.11491","title":"Constraint-Aware Reinforcement Learning via Adaptive Action Scaling","created":"2025-10-13","cited_by_count":0,"area":"deeprl"},{"id":"2510.15720","title":"ProSh: Probabilistic Shielding for Model-free Reinforcement Learning","created":"2025-10-17","cited_by_count":0,"area":"deeprl"},{"id":"2510.17564","title":"Towards a Practical Understanding of Lagrangian Methods in Safe Reinforcement Learning","created":"2025-10-20","cited_by_count":0,"area":"deeprl"},{"id":"2510.18478","title":"Safe But Not Sorry: Reducing Over-Conservatism in Safety Critics via Uncertainty-Aware Modulation","created":"2025-10-21","cited_by_count":0,"area":"deeprl"},{"id":"2511.00880","title":"KFCPO: Kronecker-Factored Approximated Constrained Policy Optimization","created":"2025-11-02","cited_by_count":0,"area":"deeprl"},{"id":"2511.16158","title":"MagBotSim: Physics-Based Simulation and Reinforcement Learning Environments for Magnetic Robotics","created":"2025-11-20","cited_by_count":0,"area":"deeprl"},{"id":"2512.23770","title":"SB-TRPO: Towards Safe Reinforcement Learning with Hard Constraints","created":"2025-12-29","cited_by_count":0,"area":"deeprl"},{"id":"2601.04686","title":"Nightmare Dreamer: Dreaming About Unsafe States And Planning Ahead","created":"2026-01-08","cited_by_count":0,"area":"deeprl"},{"id":"2602.20729","title":"Fuz-RL: A Fuzzy-Guided Robust Framework for Safe Reinforcement Learning under Uncertainty","created":"2026-02-24","cited_by_count":0,"area":"deeprl"},{"id":"2603.23565","title":"Safe Reinforcement Learning with Preference-based Constraint Inference","created":"2026-03-24","cited_by_count":0,"area":"deeprl"},{"id":"2604.04225","title":"Learning from Imperfect Demonstrations via Temporal Behavior Tree-Guided Trajectory Repair","created":"2026-04-05","cited_by_count":0,"area":"deeprl"},{"id":"2604.06522","title":"Constrained Policy Optimization for Provably Fair Order Matching","created":"2026-04-07","cited_by_count":0,"area":"deeprl"},{"id":"2604.19737","title":"Safe Continual Reinforcement Learning in Non-stationary Environments","created":"2026-04-21","cited_by_count":0,"area":"deeprl"},{"id":"2605.14174","title":"Safety-Constrained Reinforcement Learning with Post-Training Reachability Verification for Robot Navigation","created":"2026-05-13","cited_by_count":0,"area":"deeprl"},{"id":"2605.15509","title":"parallelcbf: A composable safety-filter and auditability framework for tensor-parallel reinforcement learning","created":"2026-05-15","cited_by_count":0,"area":"deeprl"},{"id":"2605.15668","title":"Viscosity-Informed Generative Actor-Critic for High-Dimensional Stochastic Optimal Control","created":"2026-05-15","cited_by_count":0,"area":"deeprl"},{"id":"2605.26452","title":"Robust Koopman Control Barrier Filters for Safe Actor-Critic Reinforcement Learning","created":"2026-05-26","cited_by_count":0,"area":"deeprl"},{"id":"2606.04749","title":"COP-Q: Safety-First Reinforcement Learning for Robot Control via Cholesky-Ordered Projection","created":"2026-06-03","cited_by_count":0,"area":"deeprl"},{"id":"2606.14029","title":"Utility-Constrained Policy Optimization","created":"2026-06-12","cited_by_count":0,"area":"deeprl"},{"id":"2606.14415","title":"CSPO: Constraint-Sensitive Policy Optimization for Safe Reinforcement Learning","created":"2026-06-12","cited_by_count":0,"area":"deeprl"},{"id":"2607.24057","title":"Constrained Reinforcement Learning Using Successor Representations","created":"2026-07-27","cited_by_count":0,"area":"deeprl"},{"id":"2608.26571","title":"Arrive and Survive: Scaling Safe Goal-Conditioned Policy Learning from One-Bit Failure Signals","created":"2026-08-27","cited_by_count":0,"area":"deeprl"},{"id":"2609.06186","title":"Spectral Prioritized Sweeping in Nonstationary Reinforcement Learning","created":"2026-09-05","cited_by_count":0,"area":"deeprl"},{"id":"2609.15315","title":"Evaluation Metrics for Safe Reinforcement Learning","created":"2026-09-14","cited_by_count":0,"area":"deeprl"},{"id":"2609.32952","title":"Constrained Flow Policy Updates: A Generalized Schr\\\"odinger Bridge View","created":"2026-09-26","cited_by_count":0,"area":"deeprl"},{"id":"2609.38065","title":"Jaxolotl: A Unified High-Performance Benchmark Suite for LTL-Based Multi-Task RL","created":"2026-09-29","cited_by_count":0,"area":"deeprl"},{"id":"2610.00778","title":"Learning Goal-Reaching Quasimetric Geometry From Finite-Time Reachability","created":"2026-09-30","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}