{"total":71,"rows":[{"id":"2404.00282","title":"Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods","created":"2024-03-30","cited_by_count":116,"area":null},{"id":"2305.09304","title":"OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning Research","created":"2023-05-16","cited_by_count":80,"area":null},{"id":"2302.07351","title":"Constrained Decision Transformer for Offline Safe Reinforcement Learning","created":"2023-02-14","cited_by_count":69,"area":"offlinerl"},{"id":"2206.03023","title":"How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via $f$-Advantage Regression","created":"2022-06-07","cited_by_count":66,"area":"offlinerl"},{"id":"2401.10700","title":"Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model","created":"2024-01-19","cited_by_count":64,"area":"offlinerl"},{"id":"2306.09303","title":"Datasets and Benchmarks for Offline Safe Reinforcement Learning","created":"2023-06-15","cited_by_count":59,"area":"offlinerl"},{"id":"2403.03185","title":"Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking","created":"2024-03-05","cited_by_count":50,"area":"alignment"},{"id":"2402.02025","title":"A Survey of Constraint Formulations in Safe Reinforcement Learning","created":"2024-02-03","cited_by_count":44,"area":"deeprl"},{"id":"2407.20109","title":"Diffusion-DICE: In-Sample Diffusion Guidance for Offline Reinforcement Learning","created":"2024-07-29","cited_by_count":42,"area":"diffusion"},{"id":"2306.00603","title":"Safe Offline Reinforcement Learning with Real-Time Budget Constraints","created":"2023-06-01","cited_by_count":28,"area":"offlinerl"},{"id":"2301.10923","title":"Trust Region-Based Safe Distributional Reinforcement Learning for Multiple Constraints","created":"2023-01-26","cited_by_count":21,"area":null},{"id":"2402.00348","title":"ODICE: Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient Update","created":"2024-02-01","cited_by_count":21,"area":"offlinerl"},{"id":"2306.03286","title":"Survival Instinct in Offline Reinforcement Learning","created":"2023-06-05","cited_by_count":20,"area":"offlinerl"},{"id":"2302.07549","title":"Deep Offline Reinforcement Learning for Real-world Treatment Optimization Applications","created":"2023-02-15","cited_by_count":17,"area":"offlinerl"},{"id":"2301.12203","title":"SaFormer: A Conditional Sequence Modeling Approach to Offline Safe Reinforcement Learning","created":"2023-01-28","cited_by_count":16,"area":"offlinerl"},{"id":"2401.14758","title":"Off-Policy Primal-Dual Safe Reinforcement Learning","created":"2024-01-26","cited_by_count":14,"area":"deeprl"},{"id":"2502.05932","title":"Skill Expansion and Composition in Parameter Space","created":"2025-02-09","cited_by_count":14,"area":null},{"id":"2412.18946","title":"Constraint-Adaptive Policy Switching for Offline Safe Reinforcement Learning","created":"2024-12-25","cited_by_count":13,"area":"offlinerl"},{"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":"2402.17217","title":"Temporal Logic Specification-Conditioned Decision Transformer for Offline Safe Reinforcement Learning","created":"2024-02-27","cited_by_count":10,"area":"offlinerl"},{"id":"2407.14653","title":"OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning","created":"2024-07-19","cited_by_count":10,"area":"offlinerl"},{"id":"2306.07818","title":"A Primal-Dual-Critic Algorithm for Offline Constrained Reinforcement Learning","created":"2023-06-13","cited_by_count":9,"area":null},{"id":"2412.15429","title":"Offline Safe Reinforcement Learning Using Trajectory Classification","created":"2024-12-19","cited_by_count":9,"area":"offlinerl"},{"id":"2410.01954","title":"ComaDICE: Offline Cooperative Multi-Agent Reinforcement Learning with Stationary Distribution Shift Regularization","created":"2024-10-02","cited_by_count":8,"area":"offlinerl"},{"id":"2412.08794","title":"Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning","created":"2024-12-11","cited_by_count":7,"area":"offlinerl"},{"id":"2403.01734","title":"Offline Goal-Conditioned Reinforcement Learning for Safety-Critical Tasks with Recovery Policy","created":"2024-03-04","cited_by_count":5,"area":"offlinerl"},{"id":"2505.00908","title":"Learning Conservative Neural Control Barrier Functions from Offline Data","created":"2025-05-01","cited_by_count":5,"area":"offlinerl"},{"id":"2512.10822","title":"V-OCBF: Learning Safety Filters from Offline Data via Value-Guided Offline Control Barrier Functions","created":"2025-12-11","cited_by_count":5,"area":"offlinerl"},{"id":"2307.11373","title":"Offline Diversity Maximization Under Imitation Constraints","created":"2023-07-21","cited_by_count":4,"area":null},{"id":"2401.00629","title":"Adversarially Trained Weighted Actor-Critic for Safe Offline Reinforcement Learning","created":"2024-01-01","cited_by_count":4,"area":"offlinerl"},{"id":"2410.07525","title":"Offline Inverse Constrained Reinforcement Learning for Safe-Critical Decision Making in Healthcare","created":"2024-10-10","cited_by_count":4,"area":null},{"id":"2504.13368","title":"An Optimal Discriminator Weighted Imitation Perspective for Reinforcement Learning","created":"2025-04-17","cited_by_count":4,"area":null},{"id":"2509.16950","title":"Temporal Logic-Based Multi-Vehicle Backdoor Attacks against Offline RL Agents in End-to-end Autonomous Driving","created":"2025-09-21","cited_by_count":4,"area":"safety"},{"id":"2603.15136","title":"Safe Flow Q-Learning: Offline Safe Reinforcement Learning with Reachability-Based Flow Policies","created":"2026-03-16","cited_by_count":4,"area":"offlinerl"},{"id":"2309.14989","title":"Tempo Adaptation in Non-stationary Reinforcement Learning","created":"2023-09-26","cited_by_count":3,"area":null},{"id":"2407.04942","title":"FOSP: Fine-tuning Offline Safe Policy through World Models","created":"2024-07-06","cited_by_count":3,"area":"wm"},{"id":"2412.04426","title":"Towards Fast Safe Online Reinforcement Learning via Policy Finetuning","created":"2024-12-05","cited_by_count":3,"area":null},{"id":"2412.08880","title":"FAWAC: Feasibility Informed Advantage Weighted Regression for Persistent Safety in Offline Reinforcement Learning","created":"2024-12-12","cited_by_count":3,"area":"offlinerl"},{"id":"2502.02205","title":"From Uncertain to Safe: Conformal Adaptation of Diffusion Models for Safe PDE Control","created":"2025-02-04","cited_by_count":3,"area":"diffusion"},{"id":"2512.08280","title":"Model-Based Diffusion Sampling for Predictive Control in Offline Decision Making","created":"2025-12-09","cited_by_count":3,"area":"diffusion"},{"id":"2405.03892","title":"Out-of-Distribution Adaptation in Offline RL: Counterfactual Reasoning via Causal Normalizing Flows","created":"2024-05-06","cited_by_count":2,"area":"offlinerl"},{"id":"2501.04426","title":"Dual-Force: Enhanced Offline Diversity Maximization under Imitation Constraints","created":"2025-01-08","cited_by_count":2,"area":null},{"id":"2503.19267","title":"NeoRL-2: Near Real-World Benchmarks for Offline Reinforcement Learning with Extended Realistic Scenarios","created":"2025-03-25","cited_by_count":2,"area":"offlinerl"},{"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":"2602.08054","title":"Epigraph-Guided Flow Matching for Safe and Performant Offline Reinforcement Learning","created":"2026-02-08","cited_by_count":2,"area":"diffusion"},{"id":"2407.13006","title":"Sparsity-based Safety Conservatism for Constrained Offline Reinforcement Learning","created":"2024-07-17","cited_by_count":1,"area":null},{"id":"2410.22585","title":"Pre-Trained Vision Models as Perception Backbones for Safety Filters in Autonomous Driving","created":"2024-10-29","cited_by_count":1,"area":"driving"},{"id":"2505.17506","title":"Offline Constrained Reinforcement Learning under Partial Data Coverage","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2506.08644","title":"Semi-gradient DICE for Offline Constrained Reinforcement Learning","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2509.25727","title":"Boundary-to-Region Supervision for Offline Safe Reinforcement Learning","created":"2025-09-30","cited_by_count":1,"area":"offlinerl"},{"id":"2510.22027","title":"Online Optimization for Offline Safe Reinforcement Learning","created":"2025-10-24","cited_by_count":1,"area":"offlinerl"},{"id":"2512.10042","title":"SEMDICE: Off-policy State Entropy Maximization via Stationary Distribution Correction Estimation","created":"2025-12-10","cited_by_count":1,"area":"deeprl"},{"id":"2512.20173","title":"Offline Safe Policy Optimization From Heterogeneous Feedback","created":"2025-12-23","cited_by_count":1,"area":"alignment"},{"id":"2603.22292","title":"Beyond Hard Constraints: Budget-Conditioned Reachability For Safe Offline Reinforcement Learning","created":"2026-03-08","cited_by_count":1,"area":"offlinerl"},{"id":"2502.12391","title":"Don't Trade Off Safety: Diffusion Regularization for Constrained Offline RL","created":"2025-02-18","cited_by_count":0,"area":"offlinerl"},{"id":"2503.12243","title":"RISE: Robust Imitation through Stochastic Encoding","created":"2025-03-15","cited_by_count":0,"area":"offlinerl"},{"id":"2505.19337","title":"Prompting Decision Transformers for Zero-Shot Reach-Avoid Policies","created":"2025-05-25","cited_by_count":0,"area":"offlinerl"},{"id":"2511.08136","title":"SafeMIL: Learning Offline Safe Imitation Policy from Non-Preferred Trajectories","created":"2025-11-11","cited_by_count":0,"area":"offlinerl"},{"id":"2602.05323","title":"GAS: Enhancing Reward-Cost Balance of Generative Model-assisted Offline Safe RL","created":"2026-02-05","cited_by_count":0,"area":"offlinerl"},{"id":"2602.08584","title":"Conditional Sequence Modeling for Safe Reinforcement Learning","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2602.17312","title":"LexiSafe: Offline Safe Reinforcement Learning with Lexicographic Safety-Reward Hierarchy","created":"2026-02-19","cited_by_count":0,"area":"offlinerl"},{"id":"2604.26516","title":"Lyapunov-Guided Self-Alignment: Test-Time Adaptation for Offline Safe Reinforcement Learning","created":"2026-04-29","cited_by_count":0,"area":"offlinerl"},{"id":"2605.01356","title":"Model-Based Proactive Cost Generation for Learning Safe Policies Offline with Limited Violation Data","created":"2026-05-02","cited_by_count":0,"area":null},{"id":"2605.02777","title":"Decoupled Guidance Diffusion for Adaptive Offline Safe Reinforcement Learning","created":"2026-05-04","cited_by_count":0,"area":"offlinerl"},{"id":"2605.31388","title":"Constrained Multi-Objective Reinforcement Learning with Max-Min Criterion","created":"2026-05-29","cited_by_count":0,"area":"deeprl"},{"id":"2606.08414","title":"PACT: Self-Evolving Physical Safety Alignment for Diffusion Policies in Embodied Manipulation","created":"2026-06-07","cited_by_count":0,"area":"diffusion"},{"id":"2606.09559","title":"Safe-RULE: Safe Reinforcement UnLEarning","created":"2026-06-08","cited_by_count":0,"area":"safety"},{"id":"2607.03903","title":"CDCP: Conditional Diffusion Model with Contextual Prompts for Multi-task Offline Safe Reinforcement Learning","created":"2026-07-04","cited_by_count":0,"area":"diffusion"},{"id":"2609.12014","title":"Certified Safety Curation: Distribution-Free Guarantees for Safe Offline Reinforcement Learning","created":"2026-09-10","cited_by_count":0,"area":"offlinerl"},{"id":"2609.18964","title":"FedGuide: Diffusion Prior Alignment and Value Baseline Guidance for Heterogeneous Federated Reinforcement Learning","created":"2026-07-22","cited_by_count":0,"area":"diffusion"},{"id":"2609.34426","title":"Q-learning Penalized Transformer for Safe Offline Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}