{"total":23,"rows":[{"id":"2302.05209","title":"A Survey on Causal Reinforcement Learning","created":"2023-02-10","cited_by_count":45,"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":"2106.00808","title":"Invariant Policy Learning: A Causal Perspective","created":"2021-06-01","cited_by_count":17,"area":null},{"id":"2107.01850","title":"Matching a Desired Causal State via Shift Interventions","created":"2021-07-05","cited_by_count":16,"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":"2206.07883","title":"Combinatorial Pure Exploration of Causal Bandits","created":"2022-06-16","cited_by_count":9,"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":"2411.02383","title":"Linear Causal Bandits: Unknown Graph and Soft Interventions","created":"2024-11-04","cited_by_count":5,"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":"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":"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":"2505.16311","title":"Generator-Mediated Bandits: Thompson Sampling for GenAI-Powered Adaptive Interventions","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2103.04215","title":"Hierarchical Causal Bandit","created":"2021-03-07","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":"2607.15577","title":"Information-Directed Sampling for Causal Bandits","created":"2026-07-17","cited_by_count":0,"area":null}],"next_cursor":null}