{"total":16,"rows":[{"id":"2302.05209","title":"A Survey on Causal Reinforcement Learning","created":"2023-02-10","cited_by_count":45,"area":null},{"id":"2303.02186","title":"Causal Deep Learning","created":"2023-03-03","cited_by_count":20,"area":null},{"id":"2106.00808","title":"Invariant Policy Learning: A Causal Perspective","created":"2021-06-01","cited_by_count":17,"area":null},{"id":"2110.12175","title":"Analysis of Thompson Sampling for Partially Observable Contextual Multi-Armed Bandits","created":"2021-10-23","cited_by_count":10,"area":null},{"id":"2310.18601","title":"Online Decision Mediation","created":"2023-10-28","cited_by_count":4,"area":null},{"id":"2502.06142","title":"Linear Bandits with Partially Observable Features","created":"2025-02-10","cited_by_count":4,"area":null},{"id":"2202.00867","title":"Efficient Algorithms for Learning to Control Bandits with Unobserved Contexts","created":"2022-02-02","cited_by_count":3,"area":null},{"id":"2204.04773","title":"Worst-case Performance of Greedy Policies in Bandits with Imperfect Context Observations","created":"2022-04-10","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":"2404.00848","title":"Predictive Performance Comparison of Decision Policies Under Confounding","created":"2024-04-01","cited_by_count":2,"area":null},{"id":"2312.12731","title":"Robustly Improving Bandit Algorithms with Confounded and Selection Biased Offline Data: A Causal Approach","created":"2023-12-20","cited_by_count":1,"area":null},{"id":"2408.14432","title":"Contextual Bandit with Herding Effects: Algorithms and Recommendation Applications","created":"2024-08-26","cited_by_count":1,"area":null},{"id":"2209.03224","title":"Dual Instrumental Method for Confounded Kernelized Bandits","created":"2022-09-07","cited_by_count":0,"area":null},{"id":"2305.18333","title":"Ranking with Popularity Bias: User Welfare under Self-Amplification Dynamics","created":"2023-05-24","cited_by_count":0,"area":null},{"id":"2505.17283","title":"Deconfounded Warm-Start Thompson Sampling with Applications to Precision Medicine","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2610.00424","title":"Target-Dependent Limits of Causal Repair: A Leading-Log Frontier in a Gaussian Model","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}