{"total":36,"rows":[{"id":"2302.05209","title":"A Survey on Causal Reinforcement Learning","created":"2023-02-10","cited_by_count":45,"area":null},{"id":"2106.02988","title":"Causal Bandits with Unknown Graph Structure","created":"2021-06-05","cited_by_count":37,"area":null},{"id":"2209.04744","title":"Active Learning for Optimal Intervention Design in Causal Models","created":"2022-09-10","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":"2208.12764","title":"Causal Bandits for Linear Structural Equation Models","created":"2022-08-26","cited_by_count":19,"area":null},{"id":"2202.05100","title":"Adaptively Exploiting d-Separators with Causal Bandits","created":"2022-02-10","cited_by_count":18,"area":null},{"id":"2206.01995","title":"Combinatorial Causal Bandits","created":"2022-06-04","cited_by_count":16,"area":null},{"id":"2107.02772","title":"A Causal Bandit Approach to Learning Good Atomic Interventions in Presence of Unobserved Confounders","created":"2021-07-06","cited_by_count":15,"area":null},{"id":"2109.10458","title":"Achieving Counterfactual Fairness for Causal Bandit","created":"2021-09-21","cited_by_count":15,"area":null},{"id":"2108.04782","title":"Bandit Algorithms for Precision Medicine","created":"2021-08-10","cited_by_count":12,"area":null},{"id":"2301.11401","title":"Causal Bandits without Graph Learning","created":"2023-01-26","cited_by_count":10,"area":null},{"id":"2206.07883","title":"Combinatorial Pure Exploration of Causal Bandits","created":"2022-06-16","cited_by_count":9,"area":null},{"id":"2102.07663","title":"Causal Markov Decision Processes: Learning Good Interventions Efficiently","created":"2021-02-15","cited_by_count":7,"area":null},{"id":"2301.13392","title":"Combinatorial Causal Bandits without Graph Skeleton","created":"2023-01-31","cited_by_count":7,"area":null},{"id":"2403.00233","title":"Causal Bandits with General Causal Models and Interventions","created":"2024-03-01","cited_by_count":7,"area":null},{"id":"2305.04638","title":"Learning Good Interventions in Causal Graphs via Covering","created":"2023-05-08","cited_by_count":5,"area":null},{"id":"2310.07518","title":"Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning","created":"2023-10-11","cited_by_count":5,"area":null},{"id":"2411.02383","title":"Linear Causal Bandits: Unknown Graph and Soft Interventions","created":"2024-11-04","cited_by_count":5,"area":null},{"id":"2411.04054","title":"Partial Structure Discovery is Sufficient for No-regret Learning in Causal Bandits","created":"2024-11-06","cited_by_count":5,"area":null},{"id":"2212.12923","title":"Linear Combinatorial Semi-Bandit with Causally Related Rewards","created":"2022-12-25","cited_by_count":4,"area":null},{"id":"2211.15355","title":"Causal Deep Reinforcement Learning Using Observational Data","created":"2022-11-28","cited_by_count":3,"area":null},{"id":"2405.07795","title":"Improved Bound for Robust Causal Bandits with Linear Models","created":"2024-05-13","cited_by_count":2,"area":null},{"id":"2407.00950","title":"Causal Bandits: The Pareto Optimal Frontier of Adaptivity, a Reduction to Linear Bandits, and Limitations around Unknown Marginals","created":"2024-07-01","cited_by_count":2,"area":null},{"id":"2510.16811","title":"Graph Learning Is Suboptimal in Causal Bandits","created":"2025-10-19","cited_by_count":2,"area":null},{"id":"2111.00886","title":"Intervention Efficient Algorithm for Two-Stage Causal MDPs","created":"2021-11-01","cited_by_count":1,"area":null},{"id":"2307.09093","title":"Non-stationary Delayed Combinatorial Semi-Bandit with Causally Related Rewards","created":"2023-07-18","cited_by_count":1,"area":null},{"id":"2405.18626","title":"Causal Contextual Bandits with Adaptive Context","created":"2024-05-28","cited_by_count":1,"area":null},{"id":"2502.02020","title":"Causal Bandit Over Unknown Graphs: Upper Confidence Bounds With Backdoor Adjustment","created":"2025-02-04","cited_by_count":1,"area":null},{"id":"2502.06577","title":"The Minimal Search Space for Conditional Causal Bandits","created":"2025-02-10","cited_by_count":1,"area":null},{"id":"2107.03263","title":"Bandits with Stochastic Experts: Constant Regret, Empirical Experts and Episodes","created":"2021-07-07","cited_by_count":0,"area":null},{"id":"2111.04272","title":"Identifying Best Fair Intervention","created":"2021-11-08","cited_by_count":0,"area":null},{"id":"2309.02287","title":"Optimal Observation-Intervention Trade-Off in Optimisation Problems with Causal Structure","created":"2023-09-05","cited_by_count":0,"area":null},{"id":"2605.08999","title":"Non-Parametric Rehearsal Learning via Conditional Mean Embeddings","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.29008","title":"Causal Intelligence for Constraint-Aware Intervention Design to Induce State Transitions","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2607.15577","title":"Information-Directed Sampling for Causal Bandits","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2610.01377","title":"Minimax Optimal Regret for Causal Logistic Bandits with Counterfactual Fairness","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}