{"total":69,"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":"2311.01223","title":"Diffusion Models for Reinforcement Learning: A Survey","created":"2023-11-02","cited_by_count":91,"area":"diffusion"},{"id":"2306.00148","title":"SafeDiffuser: Safe Planning with Diffusion Probabilistic Models","created":"2023-05-31","cited_by_count":75,"area":"diffusion"},{"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":"2310.05905","title":"TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models","created":"2023-10-09","cited_by_count":53,"area":"offlinerl"},{"id":"2402.02025","title":"A Survey of Constraint Formulations in Safe Reinforcement Learning","created":"2024-02-03","cited_by_count":44,"area":"deeprl"},{"id":"2306.00603","title":"Safe Offline Reinforcement Learning with Real-Time Budget Constraints","created":"2023-06-01","cited_by_count":28,"area":"offlinerl"},{"id":"2504.14587","title":"Generative Auto-Bidding with Value-Guided Explorations","created":"2025-04-20","cited_by_count":23,"area":null},{"id":"2306.03286","title":"Survival Instinct in Offline Reinforcement Learning","created":"2023-06-05","cited_by_count":20,"area":"offlinerl"},{"id":"2402.13777","title":"Deep Generative Models for Offline Policy Learning: Tutorial, Survey, and Perspectives on Future Directions","created":"2024-02-21","cited_by_count":20,"area":"offlinerl"},{"id":"2310.03718","title":"Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learning","created":"2023-10-05","cited_by_count":18,"area":null},{"id":"2311.10747","title":"Safety-aware Causal Representation for Trustworthy Offline Reinforcement Learning in Autonomous Driving","created":"2023-10-31","cited_by_count":17,"area":"driving"},{"id":"2406.05427","title":"Decision Mamba: A Multi-Grained State Space Model with Self-Evolution Regularization for Offline RL","created":"2024-06-08","cited_by_count":15,"area":"ssm"},{"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":"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":"2312.15127","title":"Gradient Shaping for Multi-Constraint Safe Reinforcement Learning","created":"2023-12-23","cited_by_count":10,"area":null},{"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":"2412.08794","title":"Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning","created":"2024-12-11","cited_by_count":7,"area":"offlinerl"},{"id":"2305.16209","title":"C-MCTS: Safe Planning with Monte Carlo Tree Search","created":"2023-05-25","cited_by_count":6,"area":null},{"id":"2409.09958","title":"An Offline Adaptation Framework for Constrained Multi-Objective Reinforcement Learning","created":"2024-09-16","cited_by_count":5,"area":"deeprl"},{"id":"2509.03348","title":"Generative Auto-Bidding in Large-Scale Competitive Auctions via Diffusion Completer-Aligner","created":"2025-09-03","cited_by_count":5,"area":null},{"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":"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":"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":"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":"2501.13023","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","created":"2025-01-22","cited_by_count":3,"area":null},{"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":"2508.02002","title":"Generative Large-Scale Pre-trained Models for Automated Ad Bidding Optimization","created":"2025-08-04","cited_by_count":3,"area":"moe"},{"id":"2509.25582","title":"Safe In-Context Reinforcement Learning","created":"2025-09-29","cited_by_count":3,"area":"deeprl"},{"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":"2412.10599","title":"Advances in Transformers for Robotic Applications: A Review","created":"2024-12-13","cited_by_count":2,"area":null},{"id":"2503.05035","title":"QuietPaw: Learning Quadrupedal Locomotion with Versatile Noise Preference Alignment","created":"2025-03-06","cited_by_count":2,"area":null},{"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":"2601.20116","title":"In-Context Reinforcement Learning From Suboptimal Historical Data","created":"2026-01-27","cited_by_count":2,"area":null},{"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":"2312.17194","title":"Resilient Constrained Reinforcement Learning","created":"2023-12-28","cited_by_count":1,"area":null},{"id":"2404.10064","title":"The Feasibility Theory of Constrained Reinforcement Learning: A Tutorial Study","created":"2024-04-15","cited_by_count":1,"area":"deeprl"},{"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":"2603.17092","title":"SLowRL: Safe Low-Rank Adaptation Reinforcement Learning for Locomotion","created":"2026-03-17","cited_by_count":1,"area":"deeprl"},{"id":"2607.21111","title":"TOUR: A Trajectory-Level Unlearning Benchmark for Offline Reinforcement Learning","created":"2026-07-23","cited_by_count":1,"area":"offlinerl"},{"id":"2404.02583","title":"Transformer-based Stagewise Decomposition for Large-Scale Multistage Stochastic Optimization","created":"2024-04-03","cited_by_count":0,"area":null},{"id":"2502.01778","title":"GNN-DT: Graph Neural Network Enhanced Decision Transformer for Efficient Optimization in Dynamic Environments","created":"2025-02-03","cited_by_count":0,"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":"2503.02311","title":"Target Return Optimizer for Multi-Game Decision Transformer","created":"2025-03-04","cited_by_count":0,"area":"offlinerl"},{"id":"2504.03040","title":"Safety Modulation: Enhancing Safety in Reinforcement Learning through Cost-Modulated Rewards","created":"2025-04-03","cited_by_count":0,"area":"deeprl"},{"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":"2602.13207","title":"A Safety-Constrained Reinforcement Learning Framework for Reliable Wireless Autonomy","created":"2026-01-12","cited_by_count":0,"area":"deeprl"},{"id":"2603.22315","title":"Emergency Preemption Without Online Exploration: A Decision Transformer Approach","created":"2026-03-20","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":"2605.08512","title":"MoMo: Conditioned Contrastive Representation Learning for Preference-Modulated Planning","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.21822","title":"Implicit Safety Alignment from Crowd Preferences","created":"2026-05-20","cited_by_count":0,"area":"alignment"},{"id":"2606.00838","title":"Decoupled Behavioral Cloning for Scalable Inductive Generalization in RL from Specifications","created":"2026-05-30","cited_by_count":0,"area":"offlinerl"},{"id":"2606.08312","title":"Neuro-Symbolic Injection of LTLf Constraints in Autoregressive Reinforcement Learning Policies","created":"2026-06-06","cited_by_count":0,"area":"offlinerl"},{"id":"2606.14192","title":"DRIVE: Distributional and Retrieval-Augmented Bidding with Value Evaluation","created":"2026-06-12","cited_by_count":0,"area":"offlinerl"},{"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":"2609.21550","title":"OneBid: A Unified Auto-Bidding Foundation Model for Diverse oCPX Advertising Scenarios","created":"2026-09-18","cited_by_count":0,"area":"offlinerl"},{"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}