{"total":27,"rows":[{"id":"2212.06355","title":"A Review of Off-Policy Evaluation in Reinforcement Learning","created":"2022-12-13","cited_by_count":95,"area":null},{"id":"2111.06784","title":"A Minimax Learning Approach to Off-Policy Evaluation in Confounded Partially Observable Markov Decision Processes","created":"2021-11-12","cited_by_count":36,"area":null},{"id":"2201.04735","title":"Planning in Observable POMDPs in Quasipolynomial Time","created":"2022-01-12","cited_by_count":25,"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":"2202.00916","title":"Scalable Decision-Focused Learning in Restless Multi-Armed Bandits with Application to Maternal and Child Health","created":"2022-02-02","cited_by_count":12,"area":null},{"id":"2203.16067","title":"Decision-Focused Learning without Differentiable Optimization: Learning Locally Optimized Decision Losses","created":"2022-03-30","cited_by_count":12,"area":null},{"id":"2106.04240","title":"The Medkit-Learn(ing) Environment: Medical Decision Modelling through Simulation","created":"2021-06-08","cited_by_count":11,"area":null},{"id":"2312.05250","title":"TaskMet: Task-Driven Metric Learning for Model Learning","created":"2023-12-08","cited_by_count":11,"area":null},{"id":"2310.18591","title":"Inverse Decision Modeling: Learning Interpretable Representations of Behavior","created":"2023-10-28","cited_by_count":10,"area":null},{"id":"2505.22224","title":"Solver-Free Decision-Focused Learning for Linear Optimization Problems","created":"2025-05-28","cited_by_count":9,"area":null},{"id":"2311.07633","title":"Benchmarking PtO and PnO Methods in the Predictive Combinatorial Optimization Regime","created":"2023-11-13","cited_by_count":8,"area":null},{"id":"2103.15933","title":"Learning Under Adversarial and Interventional Shifts","created":"2021-03-29","cited_by_count":3,"area":null},{"id":"2106.03279","title":"Learning MDPs from Features: Predict-Then-Optimize for Sequential Decision Problems by Reinforcement Learning","created":"2021-06-06","cited_by_count":3,"area":null},{"id":"2110.13221","title":"On Learning Prediction-Focused Mixtures","created":"2021-10-25","cited_by_count":3,"area":null},{"id":"2211.16566","title":"Relative Sparsity for Medical Decision Problems","created":"2022-11-29","cited_by_count":2,"area":null},{"id":"2301.07835","title":"Decision-Focused Evaluation: Analyzing Performance of Deployed Restless Multi-Arm Bandits","created":"2023-01-19","cited_by_count":1,"area":null},{"id":"2304.03365","title":"Decision-Focused Model-based Reinforcement Learning for Reward Transfer","created":"2023-04-06","cited_by_count":1,"area":null},{"id":"2110.15165","title":"Extracting Expert's Goals by What-if Interpretable Modeling","created":"2021-10-28","cited_by_count":0,"area":null},{"id":"2209.08682","title":"Towards Robust Off-Policy Evaluation via Human Inputs","created":"2022-09-18","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":"2403.05683","title":"Efficient Public Health Intervention Planning Using Decomposition-Based Decision-Focused Learning","created":"2024-03-08","cited_by_count":0,"area":null},{"id":"2506.09940","title":"The Sample Complexity of Online Strategic Decision Making with Information Asymmetry and Knowledge Transportability","created":"2025-06-11","cited_by_count":0,"area":null},{"id":"2506.23040","title":"Treatment, evidence, imitation, and chat","created":"2025-06-29","cited_by_count":0,"area":null},{"id":"2510.22069","title":"Neural Index Policies for Restless Multi-Action Bandits with Heterogeneous Budgets","created":"2025-10-24","cited_by_count":0,"area":null},{"id":"2605.12262","title":"Missingness-MDPs: Bridging the Theory of Missing Data and POMDPs","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2606.04632","title":"VentAgent: When LLMs Learn to Breathe -- Multi-Objective Arbitration for ARDS Ventilation","created":"2026-06-03","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}],"next_cursor":null}