{"total":95,"rows":[{"id":"2409.18343","title":"Improving Agent Behaviors with RL Fine-tuning for Autonomous Driving","created":"2024-09-26","cited_by_count":27,"area":"driving"},{"id":"2603.01162","title":"Demystifying Group Relative Policy Optimization: Its Policy Gradient is a U-Statistic","created":"2026-03-01","cited_by_count":21,"area":"lr"},{"id":"2407.05287","title":"Model-agnostic meta-learners for estimating heterogeneous treatment effects over time","created":"2024-07-07","cited_by_count":19,"area":null},{"id":"2310.15433","title":"Off-Policy Evaluation for Large Action Spaces via Policy Convolution","created":"2023-10-24","cited_by_count":14,"area":null},{"id":"2311.18207","title":"Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation","created":"2023-11-30","cited_by_count":13,"area":null},{"id":"2504.03784","title":"Robust Reinforcement Learning from Human Feedback for Large Language Models Fine-Tuning","created":"2025-04-03","cited_by_count":13,"area":"alignment"},{"id":"2506.01183","title":"Doubly Robust Alignment for Large Language Models","created":"2025-06-01","cited_by_count":12,"area":"alignment"},{"id":"2602.01058","title":"Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning","created":"2026-02-01","cited_by_count":11,"area":"lr"},{"id":"2405.21012","title":"IGC-Net for conditional average potential outcome estimation over time","created":"2024-05-31","cited_by_count":10,"area":null},{"id":"2310.08089","title":"Learning Regularized Monotone Graphon Mean-Field Games","created":"2023-10-12","cited_by_count":9,"area":null},{"id":"2404.15691","title":"Long-term Off-Policy Evaluation and Learning","created":"2024-04-24","cited_by_count":9,"area":null},{"id":"2301.11734","title":"Improving Behavioural Cloning with Positive Unlabeled Learning","created":"2023-01-27","cited_by_count":8,"area":"offlinerl"},{"id":"2405.18610","title":"DTR-Bench: An in silico Environment and Benchmark Platform for Reinforcement Learning Based Dynamic Treatment Regime","created":"2024-05-28","cited_by_count":8,"area":"deeprl"},{"id":"2503.01134","title":"Statistical Tractability of Off-policy Evaluation of History-dependent Policies in POMDPs","created":"2025-03-03","cited_by_count":8,"area":"deeprl"},{"id":"2506.09272","title":"G-Sim: Generative Simulations with Large Language Models and Gradient-Free Calibration","created":"2025-06-10","cited_by_count":8,"area":null},{"id":"2306.08719","title":"Off-policy Evaluation in Doubly Inhomogeneous Environments","created":"2023-06-14","cited_by_count":7,"area":null},{"id":"2310.18715","title":"Robust Offline Reinforcement learning with Heavy-Tailed Rewards","created":"2023-10-28","cited_by_count":7,"area":"offlinerl"},{"id":"2304.02574","title":"Conformal Off-Policy Evaluation in Markov Decision Processes","created":"2023-04-05","cited_by_count":6,"area":null},{"id":"2309.13278","title":"Distributional Shift-Aware Off-Policy Interval Estimation: A Unified Error Quantification Framework","created":"2023-09-23","cited_by_count":6,"area":null},{"id":"2310.06969","title":"Positivity-free Policy Learning with Observational Data","created":"2023-10-10","cited_by_count":6,"area":null},{"id":"2311.18206","title":"SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation","created":"2023-11-30","cited_by_count":6,"area":"offlinerl"},{"id":"2401.03301","title":"On Sample-Efficient Offline Reinforcement Learning: Data Diversity, Posterior Sampling, and Beyond","created":"2024-01-06","cited_by_count":6,"area":"offlinerl"},{"id":"2403.17285","title":"Unraveling the Interplay between Carryover Effects and Reward Autocorrelations in Switchback Experiments","created":"2024-03-26","cited_by_count":6,"area":null},{"id":"2406.00317","title":"Combining Experimental and Historical Data for Policy Evaluation","created":"2024-06-01","cited_by_count":6,"area":null},{"id":"2406.01389","title":"RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation","created":"2024-06-03","cited_by_count":6,"area":null},{"id":"2410.11711","title":"Zero-shot Model-based Reinforcement Learning using Large Language Models","created":"2024-10-15","cited_by_count":6,"area":null},{"id":"2402.08514","title":"Counterfactual Influence in Markov Decision Processes","created":"2024-02-13","cited_by_count":5,"area":null},{"id":"2601.15353","title":"Reinforcement Learning in the Real World: A Survey of Statistical Challenges and Future Directions","created":"2026-01-21","cited_by_count":5,"area":"deeprl"},{"id":"2406.19531","title":"Off-policy Evaluation with Deeply-abstracted States","created":"2024-06-27","cited_by_count":4,"area":null},{"id":"2503.09270","title":"Rule-Guided Reinforcement Learning Policy Evaluation and Improvement","created":"2025-03-12","cited_by_count":4,"area":"deeprl"},{"id":"2504.13368","title":"An Optimal Discriminator Weighted Imitation Perspective for Reinforcement Learning","created":"2025-04-17","cited_by_count":4,"area":null},{"id":"2602.08259","title":"A Statistical Framework for Alignment with Biased AI Feedback","created":"2026-02-09","cited_by_count":4,"area":"alignment"},{"id":"2605.15108","title":"Logging Policy Design for Off-Policy Evaluation","created":"2026-05-14","cited_by_count":4,"area":null},{"id":"2403.16871","title":"Conformal Off-Policy Prediction for Multi-Agent Systems","created":"2024-03-25","cited_by_count":3,"area":null},{"id":"2407.00364","title":"Medical Knowledge Integration into Reinforcement Learning Algorithms for Dynamic Treatment Regimes","created":"2024-06-29","cited_by_count":3,"area":"deeprl"},{"id":"2409.02747","title":"Tractable Offline Learning of Regular Decision Processes","created":"2024-09-04","cited_by_count":3,"area":"offlinerl"},{"id":"2410.02172","title":"Abstract Reward Processes: Leveraging State Abstraction for Consistent Off-Policy Evaluation","created":"2024-10-03","cited_by_count":3,"area":"deeprl"},{"id":"2412.04426","title":"Towards Fast Safe Online Reinforcement Learning via Policy Finetuning","created":"2024-12-05","cited_by_count":3,"area":null},{"id":"2306.04836","title":"$K$-Nearest-Neighbor Resampling for Off-Policy Evaluation in Stochastic Control","created":"2023-06-07","cited_by_count":2,"area":null},{"id":"2404.00848","title":"Predictive Performance Comparison of Decision Policies Under Confounding","created":"2024-04-01","cited_by_count":2,"area":null},{"id":"2407.17910","title":"Causal Deepsets for Off-policy Evaluation under Spatial or Spatio-temporal Interferences","created":"2024-07-25","cited_by_count":2,"area":null},{"id":"2407.19380","title":"Empowering Clinicians with Medical Decision Transformers: A Framework for Sepsis Treatment","created":"2024-07-28","cited_by_count":2,"area":null},{"id":"2411.07700","title":"Test Where Decisions Matter: Importance-driven Testing for Deep Reinforcement Learning","created":"2024-11-12","cited_by_count":2,"area":"deeprl"},{"id":"2502.16195","title":"Statistical Inference in Reinforcement Learning: A Selective Survey","created":"2025-02-22","cited_by_count":2,"area":"deeprl"},{"id":"2505.15342","title":"Policy Testing in Markov Decision Processes","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2505.20781","title":"STITCH-OPE: Trajectory Stitching with Guided Diffusion for Off-Policy Evaluation","created":"2025-05-27","cited_by_count":2,"area":"diffusion"},{"id":"2507.13608","title":"Off-Policy Evaluation and Learning for Matching Markets","created":"2025-07-18","cited_by_count":2,"area":null},{"id":"2507.18118","title":"A Two-armed Bandit Framework for A/B Testing","created":"2025-07-24","cited_by_count":2,"area":null},{"id":"2508.01203","title":"Importance Sampling is All You Need: Predict LLM's performance on new benchmark by reusing existing benchmark","created":"2025-08-02","cited_by_count":2,"area":null},{"id":"2512.03354","title":"Breaking Determinism: Stochastic Modeling for Reliable Off-Policy Evaluation in Ad Auctions","created":"2025-12-03","cited_by_count":2,"area":null},{"id":"2407.00806","title":"Benchmarks for Reinforcement Learning with Biased Offline Data and Imperfect Simulators","created":"2024-06-30","cited_by_count":1,"area":"offlinerl"},{"id":"2409.08815","title":"Deep reinforcement learning for tracking a moving target in jellyfish-like swimming","created":"2024-09-13","cited_by_count":1,"area":"deeprl"},{"id":"2501.00854","title":"A Graphical Approach to State Variable Selection in Off-policy Learning","created":"2025-01-01","cited_by_count":1,"area":null},{"id":"2505.22492","title":"Demystifying the Paradox of Importance Sampling with an Estimated History-Dependent Behavior Policy in Off-Policy Evaluation","created":"2025-05-28","cited_by_count":1,"area":"deeprl"},{"id":"2506.14439","title":"A General Framework for Off-Policy Learning with Partially-Observed Reward","created":"2025-06-17","cited_by_count":1,"area":null},{"id":"2602.01853","title":"Designing Time Series Experiments in A/B Testing with Transformer Reinforcement Learning","created":"2026-02-02","cited_by_count":1,"area":"deeprl"},{"id":"2603.18702","title":"Off-Policy Learning with Limited Supply","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2603.21485","title":"Off-Policy Evaluation for Ranking Policies under Deterministic Logging Policies","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2605.05123","title":"Adaptive Policy Selection and Fine-Tuning under Interaction Budgets for Offline-to-Online Reinforcement Learning","created":"2026-05-06","cited_by_count":1,"area":"offlinerl"},{"id":"2605.19208","title":"Precision Physical Activity Prescription via Reinforcement Learning for Functional Actions","created":"2026-05-19","cited_by_count":1,"area":"deeprl"},{"id":"2607.05375","title":"Fitted Occupancy-Ratio Evaluation without Bellman Completeness","created":"2026-07-06","cited_by_count":1,"area":"offlinerl"},{"id":"2306.14297","title":"Inference for relative sparsity","created":"2023-06-25","cited_by_count":0,"area":null},{"id":"2310.10556","title":"Sample Complexity of Preference-Based Nonparametric Off-Policy Evaluation with Deep Networks","created":"2023-10-16","cited_by_count":0,"area":"alignment"},{"id":"2311.18725","title":"AI in Pharma for Personalized Sequential Decision-Making: Methods, Applications and Opportunities","created":"2023-11-30","cited_by_count":0,"area":null},{"id":"2312.14196","title":"Optimizing Heat Alert Issuance with Reinforcement Learning","created":"2023-12-21","cited_by_count":0,"area":null},{"id":"2407.03674","title":"Short-Long Policy Evaluation with Novel Actions","created":"2024-07-04","cited_by_count":0,"area":null},{"id":"2412.10381","title":"Supervised Learning-enhanced Multi-Group Actor Critic for Live Stream Allocation in Feed","created":"2024-11-28","cited_by_count":0,"area":"deeprl"},{"id":"2503.12760","title":"SNPL: Simultaneous Policy Learning and Evaluation for Safe Multi-Objective Policy Improvement","created":"2025-03-17","cited_by_count":0,"area":"safety"},{"id":"2503.15890","title":"Time After Time: Deep-Q Effect Estimation for Interventions on When and What to do","created":"2025-03-20","cited_by_count":0,"area":null},{"id":"2504.13982","title":"When Machine Learning Meets Importance Sampling: A More Efficient Rare Event Estimation Approach","created":"2025-04-18","cited_by_count":0,"area":null},{"id":"2504.21326","title":"Q-function Decomposition with Intervention Semantics with Factored Action Spaces","created":"2025-04-30","cited_by_count":0,"area":"deeprl"},{"id":"2505.22442","title":"Fully Offline Reinforcement Learning","created":"2025-05-28","cited_by_count":0,"area":"offlinerl"},{"id":"2507.02211","title":"Dilution, Diffusion and Symbiosis in Spatial Prisoner's Dilemma with Reinforcement Learning","created":"2025-07-03","cited_by_count":0,"area":"deeprl"},{"id":"2509.19464","title":"Evaluation-Aware Reinforcement Learning","created":"2025-09-23","cited_by_count":0,"area":"deeprl"},{"id":"2509.26429","title":"An Orthogonal Learner for Individualized Outcomes in Markov Decision Processes","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2510.01508","title":"Realistic CDSS Drug Dosing with End-to-end Recurrent Q-learning for Dual Vasopressor Control","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2510.03912","title":"Generalized Fitted Q-Iteration with Clustered Data","created":"2025-10-04","cited_by_count":0,"area":"deeprl"},{"id":"2510.08571","title":"Scalable Offline Metrics for Autonomous Driving","created":"2025-10-09","cited_by_count":0,"area":"driving"},{"id":"2511.00802","title":"GrowthHacker: Automated Off-Policy Evaluation Optimization Using Code-Modifying LLM Agents","created":"2025-11-02","cited_by_count":0,"area":"agents"},{"id":"2602.02530","title":"Formulating Reinforcement Learning for Human-Robot Collaboration through Off-Policy Evaluation","created":"2026-01-27","cited_by_count":0,"area":"offlinerl"},{"id":"2602.19298","title":"ALPACA: A Reinforcement Learning Environment for Medication Repurposing and Treatment Optimization in Alzheimer's Disease","created":"2026-02-22","cited_by_count":0,"area":"deeprl"},{"id":"2603.22083","title":"A Context Engineering Framework for Improving Enterprise AI Agents based on Digital-Twin MDP","created":"2026-03-23","cited_by_count":0,"area":"agents"},{"id":"2605.18509","title":"Offline Contextual Bandits in the Presence of New Actions","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.25114","title":"Counterfactually Safe Reinforcement Learning","created":"2026-05-24","cited_by_count":0,"area":"deeprl"},{"id":"2606.00913","title":"Bandit Simulation for Average Reward Inference","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.01028","title":"A Unified Benchmark for Dynamic Medical Treatment Reinforcement Learning","created":"2026-05-31","cited_by_count":0,"area":"deeprl"},{"id":"2606.07308","title":"Off-Policy Evaluation with Strategic Agents via Local Disclosure","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.20206","title":"Off-Policy Evaluation for Missingness-Aware Policies in MDPs with Rewards Missing Not at Random","created":"2026-06-18","cited_by_count":0,"area":"offlinerl"},{"id":"2606.22510","title":"Fed-CausalDiff: Decoupled Synchronization for Federated Do-Simulation and Policy Evaluation","created":"2026-06-21","cited_by_count":0,"area":null},{"id":"2606.24160","title":"An Introduction to Causal Reinforcement Learning","created":"2026-06-23","cited_by_count":0,"area":"deeprl"},{"id":"2607.11720","title":"Active Offline-to-Online Reinforcement Learning","created":"2026-07-13","cited_by_count":0,"area":"offlinerl"},{"id":"2607.22012","title":"Cross-Domain Off-Policy Evaluation and Learning for Contextual Bandits","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2607.25241","title":"Learning from the Unseen: Offline Reinforcement Learning with Hidden Actions","created":"2026-07-28","cited_by_count":0,"area":"offlinerl"},{"id":"2608.24858","title":"Bellman Calibration for Marginalized Importance Weighting in Offline Reinforcement Learning","created":"2026-08-25","cited_by_count":0,"area":"offlinerl"},{"id":"2609.34593","title":"Deep Weighted Bellman Residual Minimization for $Q^*$ Estimation","created":"2026-09-28","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}