{"total":61,"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":"2302.05209","title":"A Survey on Causal Reinforcement Learning","created":"2023-02-10","cited_by_count":45,"area":null},{"id":"2104.12820","title":"Universal Off-Policy Evaluation","created":"2021-04-26","cited_by_count":43,"area":null},{"id":"2110.15332","title":"Proximal Reinforcement Learning: Efficient Off-Policy Evaluation in Partially Observed Markov Decision Processes","created":"2021-10-28","cited_by_count":41,"area":"offlinerl"},{"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":"2102.09907","title":"Instrumental Variable Value Iteration for Causal Offline Reinforcement Learning","created":"2021-02-19","cited_by_count":35,"area":"offlinerl"},{"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":"2307.01452","title":"Causal Reinforcement Learning: A Survey","created":"2023-07-04","cited_by_count":23,"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":"2212.14468","title":"An Instrumental Variable Approach to Confounded Off-Policy Evaluation","created":"2022-12-29","cited_by_count":20,"area":null},{"id":"2209.10064","title":"Off-Policy Evaluation for Episodic Partially Observable Markov Decision Processes under Non-Parametric Models","created":"2022-09-21","cited_by_count":18,"area":null},{"id":"2111.06721","title":"Causal Multi-Agent Reinforcement Learning: Review and Open Problems","created":"2021-11-12","cited_by_count":16,"area":null},{"id":"2110.06539","title":"On Covariate Shift of Latent Confounders in Imitation and Reinforcement Learning","created":"2021-10-13","cited_by_count":14,"area":"offlinerl"},{"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":"2302.00662","title":"Robust Fitted-Q-Evaluation and Iteration under Sequentially Exogenous Unobserved Confounders","created":"2023-02-01","cited_by_count":13,"area":"offlinerl"},{"id":"2306.03929","title":"Finding Counterfactually Optimal Action Sequences in Continuous State Spaces","created":"2023-06-06","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":"2211.16583","title":"Offline Policy Evaluation and Optimization under Confounding","created":"2022-11-29","cited_by_count":12,"area":"offlinerl"},{"id":"2301.04939","title":"Safe Policy Improvement for POMDPs via Finite-State Controllers","created":"2023-01-12","cited_by_count":12,"area":null},{"id":"2306.14351","title":"Comparing Causal Frameworks: Potential Outcomes, Structural Models, Graphs, and Abstractions","created":"2023-06-25","cited_by_count":11,"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":"2208.11040","title":"Strategic Decision-Making in the Presence of Information Asymmetry: Provably Efficient RL with Algorithmic Instruments","created":"2022-08-23","cited_by_count":9,"area":"offlinerl"},{"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":"2102.07663","title":"Causal Markov Decision Processes: Learning Good Interventions Efficiently","created":"2021-02-15","cited_by_count":7,"area":null},{"id":"2306.01157","title":"Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding","created":"2023-06-01","cited_by_count":7,"area":"offlinerl"},{"id":"2510.21110","title":"Confounding Robust Deep Reinforcement Learning: A Causal Approach","created":"2025-10-24","cited_by_count":7,"area":"deeprl"},{"id":"2112.04571","title":"Ambiguous Dynamic Treatment Regimes: A Reinforcement Learning Approach","created":"2021-12-08","cited_by_count":6,"area":null},{"id":"2310.07123","title":"Off-Policy Evaluation for Human Feedback","created":"2023-10-11","cited_by_count":6,"area":"alignment"},{"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":"2502.13022","title":"Efficient and Sharp Off-Policy Learning under Unobserved Confounding","created":"2025-02-18","cited_by_count":6,"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":"2405.08498","title":"Learning Decision Policies with Instrumental Variables through Double Machine Learning","created":"2024-05-14","cited_by_count":5,"area":null},{"id":"2412.05783","title":"Two-way Deconfounder for Off-policy Evaluation in Causal Reinforcement Learning","created":"2024-12-08","cited_by_count":5,"area":"deeprl"},{"id":"2201.08262","title":"Generalizing Off-Policy Evaluation From a Causal Perspective For Sequential Decision-Making","created":"2022-01-20","cited_by_count":4,"area":null},{"id":"2309.04222","title":"Offline Recommender System Evaluation under Unobserved Confounding","created":"2023-09-08","cited_by_count":4,"area":null},{"id":"2310.08824","title":"Confounding-Robust Policy Improvement with Human-AI Teams","created":"2023-10-13","cited_by_count":4,"area":null},{"id":"2401.11353","title":"Distributionally Robust Policy Evaluation under General Covariate Shift in Contextual Bandits","created":"2024-01-21","cited_by_count":4,"area":null},{"id":"2606.04421","title":"Trivium: Temporal Regret as a First-Class Objective for Causal-Memory Controllers","created":"2026-06-03","cited_by_count":4,"area":"agents"},{"id":"2103.15933","title":"Learning Under Adversarial and Interventional Shifts","created":"2021-03-29","cited_by_count":3,"area":null},{"id":"2209.15448","title":"Blessing from Human-AI Interaction: Super Reinforcement Learning in Confounded Environments","created":"2022-09-29","cited_by_count":3,"area":null},{"id":"2301.08649","title":"Off-Policy Evaluation with Out-of-Sample Guarantees","created":"2023-01-20","cited_by_count":3,"area":null},{"id":"2404.00099","title":"Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes","created":"2024-03-29","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":"2605.09168","title":"CIVeX: Causal Intervention Verification for Language Agents","created":"2026-05-09","cited_by_count":3,"area":"agents"},{"id":"2301.07210","title":"Causal Falsification of Digital Twins","created":"2023-01-17","cited_by_count":2,"area":null},{"id":"2301.10330","title":"Off-Policy Evaluation for Action-Dependent Non-Stationary Environments","created":"2023-01-24","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":"2602.02847","title":"Causal Flow Q-Learning for Robust Offline Reinforcement Learning","created":"2026-02-02","cited_by_count":2,"area":"diffusion"},{"id":"2111.11113","title":"Case-based off-policy policy evaluation using prototype learning","created":"2021-11-22","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":"2209.08682","title":"Towards Robust Off-Policy Evaluation via Human Inputs","created":"2022-09-18","cited_by_count":0,"area":null},{"id":"2212.12167","title":"Offline Reinforcement Learning for Human-Guided Human-Machine Interaction with Private Information","created":"2022-12-23","cited_by_count":0,"area":"offlinerl"},{"id":"2403.11841","title":"Pessimistic Causal Reinforcement Learning with Mediators for Confounded Offline Data","created":"2024-03-18","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":"2412.07895","title":"How Should We Represent History in Interpretable Models of Clinical Policies?","created":"2024-12-10","cited_by_count":0,"area":null},{"id":"2412.20638","title":"Predicting Long Term Sequential Policy Value Using Softer Surrogates","created":"2024-12-30","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":"2506.05445","title":"Causal Policy Learning in Reinforcement Learning: Backdoor-Adjusted Soft Actor-Critic","created":"2025-06-05","cited_by_count":0,"area":"deeprl"},{"id":"2608.02893","title":"Robust Counterfactual Policy Optimisation via Nondeterministic Causal Models","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.30442","title":"Confounding Masquerading as Improvement: A Systematic Evaluation of Offline Reinforcement Learning for Stroke Antithrombotic Treatment in a 129,000-Patient Registry","created":"2026-08-31","cited_by_count":0,"area":"offlinerl"},{"id":"2610.16280","title":"agent-risk: Risk Assessment for Changes to AI Agents","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}