{"total":103,"rows":[{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181,"area":null},{"id":"2103.16596","title":"Benchmarks for Deep Off-Policy Evaluation","created":"2021-03-30","cited_by_count":89,"area":null},{"id":"2202.00665","title":"Tutorial on amortized optimization","created":"2022-02-01","cited_by_count":83,"area":null},{"id":"2204.08957","title":"COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation","created":"2022-04-19","cited_by_count":71,"area":null},{"id":"2209.07089","title":"Constrained Update Projection Approach to Safe Policy Optimization","created":"2022-09-15","cited_by_count":58,"area":null},{"id":"2106.09110","title":"Safe Reinforcement Learning Using Advantage-Based Intervention","created":"2021-06-16","cited_by_count":47,"area":null},{"id":"2107.12045","title":"How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review","created":"2021-07-26","cited_by_count":39,"area":null},{"id":"2105.04646","title":"Deeply-Debiased Off-Policy Interval Estimation","created":"2021-05-10","cited_by_count":36,"area":null},{"id":"2104.13877","title":"Autoregressive Dynamics Models for Offline Policy Evaluation and Optimization","created":"2021-04-28","cited_by_count":33,"area":null},{"id":"2201.06169","title":"On Well-posedness and Minimax Optimal Rates of Nonparametric Q-function Estimation in Off-policy Evaluation","created":"2022-01-17","cited_by_count":33,"area":null},{"id":"2201.12417","title":"Why Should I Trust You, Bellman? The Bellman Error is a Poor Replacement for Value Error","created":"2022-01-28","cited_by_count":32,"area":null},{"id":"2202.10589","title":"Off-Policy Confidence Interval Estimation with Confounded Markov Decision Process","created":"2022-02-22","cited_by_count":31,"area":null},{"id":"2107.05216","title":"A Simple Reward-free Approach to Constrained Reinforcement Learning","created":"2021-07-12","cited_by_count":30,"area":null},{"id":"2105.03863","title":"Towards Theoretical Understandings of Robust Markov Decision Processes: Sample Complexity and Asymptotics","created":"2021-05-09","cited_by_count":27,"area":null},{"id":"2106.10251","title":"Active Offline Policy Selection","created":"2021-06-18","cited_by_count":26,"area":null},{"id":"2102.13028","title":"Batched Neural Bandits","created":"2021-02-25","cited_by_count":22,"area":null},{"id":"2105.10148","title":"On Instrumental Variable Regression for Deep Offline Policy Evaluation","created":"2021-05-21","cited_by_count":22,"area":null},{"id":"2207.13081","title":"Future-Dependent Value-Based Off-Policy Evaluation in POMDPs","created":"2022-07-26","cited_by_count":21,"area":null},{"id":"2202.07565","title":"CUP: A Conservative Update Policy Algorithm for Safe Reinforcement Learning","created":"2022-02-15","cited_by_count":20,"area":null},{"id":"2212.14468","title":"An Instrumental Variable Approach to Confounded Off-Policy Evaluation","created":"2022-12-29","cited_by_count":20,"area":null},{"id":"2109.05439","title":"Concave Utility Reinforcement Learning with Zero-Constraint Violations","created":"2021-09-12","cited_by_count":19,"area":null},{"id":"2206.09546","title":"Policy Optimization with Linear Temporal Logic Constraints","created":"2022-06-20","cited_by_count":19,"area":null},{"id":"2202.04970","title":"Off-Policy Fitted Q-Evaluation with Differentiable Function Approximators: Z-Estimation and Inference Theory","created":"2022-02-10","cited_by_count":18,"area":null},{"id":"2201.10081","title":"Dynamics-Aware Comparison of Learned Reward Functions","created":"2022-01-25","cited_by_count":17,"area":null},{"id":"2111.14552","title":"Robust On-Policy Sampling for Data-Efficient Policy Evaluation in Reinforcement Learning","created":"2021-11-29","cited_by_count":15,"area":null},{"id":"2206.06711","title":"Conformal Off-policy Prediction","created":"2022-06-14","cited_by_count":14,"area":null},{"id":"2301.13734","title":"Efficient Policy Evaluation with Offline Data Informed Behavior Policy Design","created":"2023-01-31","cited_by_count":14,"area":null},{"id":"2302.12537","title":"Why Target Networks Stabilise Temporal Difference Methods","created":"2023-02-24","cited_by_count":13,"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":"2204.00956","title":"Model-Free and Model-Based Policy Evaluation when Causality is Uncertain","created":"2022-04-02","cited_by_count":12,"area":null},{"id":"2206.02887","title":"Sample Complexity of Nonparametric Off-Policy Evaluation on Low-Dimensional Manifolds using Deep Networks","created":"2022-06-06","cited_by_count":12,"area":null},{"id":"2302.06064","title":"Provably Safe Reinforcement Learning with Step-wise Violation Constraints","created":"2023-02-13","cited_by_count":11,"area":null},{"id":"2109.13377","title":"Model-Free Reinforcement Learning for Optimal Control of MarkovDecision Processes Under Signal Temporal Logic Specifications","created":"2021-09-27","cited_by_count":10,"area":null},{"id":"2402.14703","title":"On the Curses of Future and History in Future-dependent Value Functions for Off-policy Evaluation","created":"2024-02-22","cited_by_count":10,"area":null},{"id":"2203.07671","title":"Safe Neurosymbolic Learning with Differentiable Symbolic Execution","created":"2022-03-15","cited_by_count":9,"area":null},{"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":"2210.15543","title":"Beyond the Return: Off-policy Function Estimation under User-specified Error-measuring Distributions","created":"2022-10-27","cited_by_count":8,"area":null},{"id":"2212.07486","title":"Scaling Marginalized Importance Sampling to High-Dimensional State-Spaces via State Abstraction","created":"2022-12-14","cited_by_count":7,"area":null},{"id":"2301.02220","title":"Value Enhancement of Reinforcement Learning via Efficient and Robust Trust Region Optimization","created":"2023-01-05","cited_by_count":7,"area":null},{"id":"2306.08719","title":"Off-policy Evaluation in Doubly Inhomogeneous Environments","created":"2023-06-14","cited_by_count":7,"area":null},{"id":"2310.17146","title":"Counterfactual-Augmented Importance Sampling for Semi-Offline Policy Evaluation","created":"2023-10-26","cited_by_count":7,"area":null},{"id":"2110.10081","title":"Stateful Offline Contextual Policy Evaluation and Learning","created":"2021-10-19","cited_by_count":6,"area":null},{"id":"2301.12056","title":"Variational Latent Branching Model for Off-Policy Evaluation","created":"2023-01-28","cited_by_count":6,"area":null},{"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":"2406.00317","title":"Combining Experimental and Historical Data for Policy Evaluation","created":"2024-06-01","cited_by_count":6,"area":null},{"id":"2207.06147","title":"A Near-Optimal Primal-Dual Method for Off-Policy Learning in CMDP","created":"2022-07-13","cited_by_count":5,"area":null},{"id":"2302.09212","title":"HOPE: Human-Centric Off-Policy Evaluation for E-Learning and Healthcare","created":"2023-02-18","cited_by_count":5,"area":null},{"id":"2505.20130","title":"Balancing Interference and Correlation in Spatial Experimental Designs: A Causal Graph Cut Approach","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2310.18409","title":"State-Action Similarity-Based Representations for Off-Policy Evaluation","created":"2023-10-27","cited_by_count":4,"area":null},{"id":"2406.19531","title":"Off-policy Evaluation with Deeply-abstracted States","created":"2024-06-27","cited_by_count":4,"area":null},{"id":"2106.03934","title":"Offline Policy Comparison under Limited Historical Agent-Environment Interactions","created":"2021-06-07","cited_by_count":3,"area":null},{"id":"2107.01360","title":"Supervised Off-Policy Ranking","created":"2021-07-03","cited_by_count":3,"area":null},{"id":"2309.02669","title":"Marketing Budget Allocation with Offline Constrained Deep Reinforcement Learning","created":"2023-09-06","cited_by_count":3,"area":null},{"id":"2312.11551","title":"Probabilistic Offline Policy Ranking with Approximate Bayesian Computation","created":"2023-12-17","cited_by_count":3,"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":"2405.17708","title":"OPERA: Automatic Offline Policy Evaluation with Re-weighted Aggregates of Multiple Estimators","created":"2024-05-27","cited_by_count":3,"area":null},{"id":"2412.08052","title":"CANDOR: Counterfactual ANnotated DOubly Robust Off-Policy Evaluation","created":"2024-12-11","cited_by_count":3,"area":null},{"id":"2505.00304","title":"Reinforcement Learning with Continuous Actions Under Unmeasured Confounding","created":"2025-05-01","cited_by_count":3,"area":null},{"id":"2110.02421","title":"Explaining Off-Policy Actor-Critic From A Bias-Variance Perspective","created":"2021-10-06","cited_by_count":2,"area":null},{"id":"2112.11532","title":"Off Environment Evaluation Using Convex Risk Minimization","created":"2021-12-21","cited_by_count":2,"area":null},{"id":"2211.05361","title":"Safety-Constrained Policy Transfer with Successor Features","created":"2022-11-10","cited_by_count":2,"area":null},{"id":"2301.13348","title":"A Reinforcement Learning Framework for Dynamic Mediation Analysis","created":"2023-01-31","cited_by_count":2,"area":null},{"id":"2303.10180","title":"Towards Real-World Applications of Personalized Anesthesia Using Policy Constraint Q Learning for Propofol Infusion Control","created":"2023-03-17","cited_by_count":2,"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":"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":"2412.10915","title":"Canopy: Property-Driven Learning for Congestion Control","created":"2024-12-14","cited_by_count":2,"area":null},{"id":"2507.06961","title":"Off-Policy Evaluation Under Nonignorable Missing Data","created":"2025-07-09","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":"2512.23805","title":"Fitted Q-Evaluation without Bellman Completeness via Occupancy Weighting","created":"2025-12-29","cited_by_count":2,"area":null},{"id":"2601.05597","title":"Good Allocations from Bad Estimates","created":"2026-01-09","cited_by_count":2,"area":null},{"id":"2111.05670","title":"DeCOM: Decomposed Policy for Constrained Cooperative Multi-Agent Reinforcement Learning","created":"2021-11-10","cited_by_count":1,"area":null},{"id":"2201.02300","title":"Hyperparameter Selection Methods for Fitted Q-Evaluation with Error Guarantee","created":"2022-01-07","cited_by_count":1,"area":null},{"id":"2306.09800","title":"$\\pi2\\text{vec}$: Policy Representations with Successor Features","created":"2023-06-16","cited_by_count":1,"area":null},{"id":"2504.17277","title":"ExOSITO: Explainable Off-Policy Learning with Side Information for Intensive Care Unit Blood Test Orders","created":"2025-04-24","cited_by_count":1,"area":null},{"id":"2505.17506","title":"Offline Constrained Reinforcement Learning under Partial Data Coverage","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2603.03191","title":"A Covering Framework for Offline POMDPs Learning using Belief Space Metric","created":"2026-03-03","cited_by_count":1,"area":null},{"id":"2108.12916","title":"A Policy Efficient Reduction Approach to Convex Constrained Deep Reinforcement Learning","created":"2021-08-29","cited_by_count":0,"area":null},{"id":"2212.08302","title":"Safe Evaluation For Offline Learning: Are We Ready To Deploy?","created":"2022-12-16","cited_by_count":0,"area":null},{"id":"2301.00927","title":"Deep Spectral Q-learning with Application to Mobile Health","created":"2023-01-03","cited_by_count":0,"area":null},{"id":"2301.03183","title":"Minimax Weight Learning for Absorbing MDPs","created":"2023-01-09","cited_by_count":0,"area":null},{"id":"2306.14297","title":"Inference for relative sparsity","created":"2023-06-25","cited_by_count":0,"area":null},{"id":"2309.15737","title":"Provably Efficient Exploration in Constrained Reinforcement Learning:Posterior Sampling Is All You Need","created":"2023-09-27","cited_by_count":0,"area":null},{"id":"2312.15458","title":"Conservative Exploration for Policy Optimization via Off-Policy Policy Evaluation","created":"2023-12-24","cited_by_count":0,"area":null},{"id":"2405.14116","title":"Learning Multimodal Confidence for Intention Recognition in Human-Robot Interaction","created":"2024-05-23","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":"2410.01643","title":"Stable Offline Value Function Learning with Bisimulation-based Representations","created":"2024-10-02","cited_by_count":0,"area":null},{"id":"2410.20017","title":"Off-Policy Selection for Initiating Human-Centric Experimental Design","created":"2024-10-26","cited_by_count":0,"area":null},{"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":"2505.00913","title":"Fine-Tuning without Performance Degradation","created":"2025-05-01","cited_by_count":0,"area":null},{"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":"2510.07635","title":"Safely Exploring Novel Actions in Recommender Systems via Deployment-Efficient Policy Learning","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2510.08350","title":"DeepEN: A Deep Reinforcement Learning Framework for Personalized Enteral Nutrition in Critical Care","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2602.12379","title":"Deep Doubly Debiased Longitudinal Effect Estimation with ICE G-Computation","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2604.21235","title":"Learning Dynamic Representations and Policies from Multimodal Clinical Time-Series with Informative Missingness","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2605.06474","title":"Q-MMR: Off-Policy Evaluation via Recursive Reweighting and Moment Matching","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.14284","title":"Smooth Multi-Policy Causal Effect Estimation in Longitudinal Settings","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2606.25923","title":"$\\text{DT}^2$: Decision-Targeted Digital Twins","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2608.16482","title":"Offline Reinforcement Learning for Hemodynamic Management of Sepsis in the ICU: a MIMIC-IV Study with Dual Off-Policy Evaluation","created":"2026-08-17","cited_by_count":0,"area":null}],"next_cursor":"100"}