{"total":25,"rows":[{"id":"2302.05209","title":"A Survey on Causal Reinforcement Learning","created":"2023-02-10","cited_by_count":45,"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":"2410.15319","title":"Causality for Large Language Models","created":"2024-10-20","cited_by_count":25,"area":null},{"id":"2307.01452","title":"Causal Reinforcement Learning: A Survey","created":"2023-07-04","cited_by_count":23,"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":"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":"2306.16021","title":"Structure in Deep Reinforcement Learning: A Survey and Open Problems","created":"2023-06-28","cited_by_count":16,"area":null},{"id":"2104.07822","title":"Estimating and Improving Dynamic Treatment Regimes With a Time-Varying Instrumental Variable","created":"2021-04-15","cited_by_count":13,"area":null},{"id":"2302.05404","title":"Minimax Instrumental Variable Regression and $L_2$ Convergence Guarantees without Identification or Closedness","created":"2023-02-10","cited_by_count":13,"area":null},{"id":"2212.05778","title":"Instrumental Variables in Causal Inference and Machine Learning: A Survey","created":"2022-12-12","cited_by_count":10,"area":null},{"id":"2411.19653","title":"Nonparametric Instrumental Regression via Kernel Methods is Minimax Optimal","created":"2024-11-29","cited_by_count":8,"area":null},{"id":"2212.09494","title":"Optimal Treatment Regimes for Proximal Causal Learning","created":"2022-12-19","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":"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":"2501.04898","title":"Optimality and Adaptivity of Deep Neural Features for Instrumental Variable Regression","created":"2025-01-09","cited_by_count":3,"area":null},{"id":"2106.03340","title":"Instrument Space Selection for Kernel Maximum Moment Restriction","created":"2021-06-07","cited_by_count":2,"area":null},{"id":"2303.11187","title":"A Unified Framework of Policy Learning for Contextual Bandit with Confounding Bias and Missing Observations","created":"2023-03-20","cited_by_count":2,"area":null},{"id":"2507.09742","title":"Causality-informed Anomaly Detection in Partially Observable Sensor Networks: Moving beyond Correlations","created":"2025-07-13","cited_by_count":2,"area":null},{"id":"2209.05186","title":"Statistical Estimation of Confounded Linear MDPs: An Instrumental Variable Approach","created":"2022-09-12","cited_by_count":0,"area":null},{"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":"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":"2602.05139","title":"Adaptive Exploration for Latent-State Bandits","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2603.17577","title":"Identifying Latent Actions and Dynamics from Offline Data via Demonstrator Diversity","created":"2026-03-18","cited_by_count":0,"area":null}],"next_cursor":null}