{"total":101,"rows":[{"id":"2206.01152","title":"Causal Structure Learning: a Combinatorial Perspective","created":"2022-06-02","cited_by_count":46,"area":null},{"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":"2207.06272","title":"Hindsight Learning for MDPs with Exogenous Inputs","created":"2022-07-13","cited_by_count":26,"area":null},{"id":"2211.10257","title":"Model-based Causal Bayesian Optimization","created":"2022-11-18","cited_by_count":26,"area":null},{"id":"2306.03928","title":"Designing Decision Support Systems Using Counterfactual Prediction Sets","created":"2023-06-06","cited_by_count":26,"area":null},{"id":"2210.16913","title":"Revisiting Simple Regret: Fast Rates for Returning a Good Arm","created":"2022-10-30","cited_by_count":25,"area":null},{"id":"2202.02896","title":"Evaluation Methods and Measures for Causal Learning Algorithms","created":"2022-02-07","cited_by_count":23,"area":null},{"id":"2307.01452","title":"Causal Reinforcement Learning: A Survey","created":"2023-07-04","cited_by_count":23,"area":null},{"id":"2303.02186","title":"Causal Deep Learning","created":"2023-03-03","cited_by_count":20,"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":"2106.00808","title":"Invariant Policy Learning: A Causal Perspective","created":"2021-06-01","cited_by_count":17,"area":null},{"id":"2110.13891","title":"Dynamic Causal Bayesian Optimization","created":"2021-10-26","cited_by_count":17,"area":null},{"id":"2205.13930","title":"Fairness and Welfare Quantification for Regret in Multi-Armed Bandits","created":"2022-05-27","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":"2109.10458","title":"Achieving Counterfactual Fairness for Causal Bandit","created":"2021-09-21","cited_by_count":15,"area":null},{"id":"2206.04551","title":"A Relational Intervention Approach for Unsupervised Dynamics Generalization in Model-Based Reinforcement Learning","created":"2022-06-09","cited_by_count":15,"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":"2205.10032","title":"Survey on Fair Reinforcement Learning: Theory and Practice","created":"2022-05-20","cited_by_count":14,"area":null},{"id":"2208.10981","title":"Causal Entropy Optimization","created":"2022-08-23","cited_by_count":13,"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":"2306.07858","title":"Additive Causal Bandits with Unknown Graph","created":"2023-06-13","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":"2106.05074","title":"Operationalizing Complex Causes: A Pragmatic View of Mediation","created":"2021-06-09","cited_by_count":8,"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":"2306.04027","title":"Intervention Generalization: A View from Factor Graph Models","created":"2023-06-06","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":"2305.19158","title":"Competing for Shareable Arms in Multi-Player Multi-Armed Bandits","created":"2023-05-30","cited_by_count":6,"area":null},{"id":"2305.20011","title":"Constrained Causal Bayesian Optimization","created":"2023-05-31","cited_by_count":6,"area":null},{"id":"2404.17493","title":"Causally Abstracted Multi-armed Bandits","created":"2024-04-26","cited_by_count":6,"area":null},{"id":"2406.10738","title":"Adaptive Experimentation When You Can't Experiment","created":"2024-06-15","cited_by_count":6,"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":"2306.06409","title":"Functional Causal Bayesian Optimization","created":"2023-06-10","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":"2402.08514","title":"Counterfactual Influence in Markov Decision Processes","created":"2024-02-13","cited_by_count":5,"area":null},{"id":"2403.11219","title":"Causality from Bottom to Top: A Survey","created":"2024-03-17","cited_by_count":5,"area":null},{"id":"2409.11521","title":"Partially Observable Contextual Bandits with Linear Payoffs","created":"2024-09-17","cited_by_count":5,"area":null},{"id":"2409.18909","title":"Best Arm Identification with Minimal Regret","created":"2024-09-27","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":"2503.07555","title":"Graph-Dependent Regret Bounds in Multi-Armed Bandits with Interference","created":"2025-03-10","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":"2310.19794","title":"Robust Causal Bandits for Linear Models","created":"2023-10-30","cited_by_count":4,"area":null},{"id":"2401.07578","title":"Confounded Budgeted Causal Bandits","created":"2024-01-15","cited_by_count":4,"area":null},{"id":"2502.20153","title":"Transfer Learning in Latent Contextual Bandits with Covariate Shift Through Causal Transportability","created":"2025-02-27","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":"2206.04091","title":"Uplifting Bandits","created":"2022-06-08","cited_by_count":2,"area":null},{"id":"2301.12412","title":"Contextual Causal Bayesian Optimisation","created":"2023-01-29","cited_by_count":2,"area":null},{"id":"2306.13732","title":"Reinforcement Learning with Temporal-Logic-Based Causal Diagrams","created":"2023-06-23","cited_by_count":2,"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":"2408.11240","title":"Asymmetric Graph Error Control with Low Complexity in Causal Bandits","created":"2024-08-20","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":"2602.11675","title":"Epistemic Regret Minimization: Label-Free Causal Critique Beyond Outcome Reward","created":"2026-02-12","cited_by_count":2,"area":"lr"},{"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":"2307.14138","title":"Piecewise-Stationary Combinatorial Semi-Bandit with Causally Related Rewards","created":"2023-07-26","cited_by_count":1,"area":null},{"id":"2308.09248","title":"Active and Passive Causal Inference Learning","created":"2023-08-18","cited_by_count":1,"area":null},{"id":"2312.13875","title":"Best Arm Identification in Batched Multi-armed Bandit Problems","created":"2023-12-21","cited_by_count":1,"area":null},{"id":"2403.04221","title":"Why Online Reinforcement Learning is Causal","created":"2024-03-07","cited_by_count":1,"area":"offlinerl"},{"id":"2405.18626","title":"Causal Contextual Bandits with Adaptive Context","created":"2024-05-28","cited_by_count":1,"area":null},{"id":"2410.01822","title":"The Importance of Causality in Decision Making: A Perspective on Recommender Systems","created":"2024-09-16","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":"2509.04296","title":"Using causal abstractions to accelerate decision-making in complex bandit problems","created":"2025-09-04","cited_by_count":1,"area":null},{"id":"2510.08207","title":"DODO: Causal Structure Learning with Budgeted Interventions","created":"2025-10-09","cited_by_count":1,"area":null},{"id":"2510.22819","title":"Last-Iterate Analyses of FTRL with the 1/2-Tsallis Entropy in Stochastic Bandits","created":"2025-10-26","cited_by_count":1,"area":null},{"id":"2511.02944","title":"Power Constrained Nonstationary Bandits with Habituation and Recovery Dynamics","created":"2025-11-04","cited_by_count":1,"area":null},{"id":"2511.17953","title":"On Transportability for Structural Causal Bandits","created":"2025-11-22","cited_by_count":1,"area":null},{"id":"2512.18135","title":"Unifying Causal Reinforcement Learning: Survey, Taxonomy, Algorithms and Applications","created":"2025-12-19","cited_by_count":1,"area":"deeprl"},{"id":"2607.05813","title":"Contextual Procurement Auctions with Bandit Learning","created":"2026-07-07","cited_by_count":1,"area":null},{"id":"2103.04215","title":"Hierarchical Causal Bandit","created":"2021-03-07","cited_by_count":0,"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":"2112.01819","title":"Chronological Causal Bandits","created":"2021-12-03","cited_by_count":0,"area":null},{"id":"2209.03224","title":"Dual Instrumental Method for Confounded Kernelized Bandits","created":"2022-09-07","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":"2312.16307","title":"Incentive-Aware Synthetic Control: Accurate Counterfactual Estimation via Incentivized Exploration","created":"2023-12-26","cited_by_count":0,"area":null},{"id":"2403.15524","title":"PPA-Game: Characterizing and Learning Competitive Dynamics Among Online Content Creators","created":"2024-03-22","cited_by_count":0,"area":null},{"id":"2407.16239","title":"Identifiable Latent Bandits: Leveraging observational data for personalized decision-making","created":"2024-07-23","cited_by_count":0,"area":null},{"id":"2503.19554","title":"Causal Bayesian Optimization with Unknown Graphs","created":"2025-03-25","cited_by_count":0,"area":null},{"id":"2505.04200","title":"Estimating Causal Effects in Networks with Cluster-Based Bandits","created":"2025-05-07","cited_by_count":0,"area":null},{"id":"2508.02812","title":"Evaluating and Learning Robust Bandit Policies Under Uncertain Causal Mechanisms","created":"2025-08-04","cited_by_count":0,"area":null},{"id":"2601.14333","title":"Hierarchical Contextual Uplift Bandits for Catalog Personalization","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2605.07057","title":"From Causal Graphs to Markovian States: Multi-Order State Exposure for Deep RL","created":"2026-05-08","cited_by_count":0,"area":"deeprl"},{"id":"2605.08999","title":"Non-Parametric Rehearsal Learning via Conditional Mean Embeddings","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.20040","title":"Active Context Selection Improves Simple Regret in Contextual Bandits","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2606.19750","title":"Manifold Bandits: Bayesian Curriculum Learning over the Latent Geometry of Large Language Models","created":"2026-06-18","cited_by_count":0,"area":"lr"},{"id":"2607.04315","title":"Fixed-Confidence Best-Arm Identification for Causal Mediation Analysis","created":"2026-07-05","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":"2608.07809","title":"CausalNav: Reliability-Certified Causal World Models for Control under Physical-Parameter Shift","created":"2026-08-07","cited_by_count":0,"area":"wm"},{"id":"2608.21993","title":"Gated Decoupled Compositional Bandits: A Unified Theory of Contextual Bandits with Supervised-Calibrated Action Scaling and Pre-Execution Gating","created":"2026-08-22","cited_by_count":0,"area":"alignment"},{"id":"2609.17942","title":"On the Identifiability of Mixed Ordinal and Exponential Family Causal DAGs under Linear Parametric Models","created":"2026-09-16","cited_by_count":0,"area":null}],"next_cursor":"100"}