Causal Bandits

Latest papers

8 papers0 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Online Causal Configuration for Networked Systems via Doubly Robust Steady-State Learning
Nov 6, 2026Yuli Liu, Zhiheng ZhangCausal Bandits Causal Inference
Smart Ocean Technology, University of Macau, Macao SAR, China · School of Statistics and Data Science, Shanghai University of Finance and Economics Shanghai 200433, P.R. China · Institute of Big Data Research, Shanghai University of Finance and Economics Shanghai 200433, P.R. China
Minimax Optimal Regret for Causal Logistic Bandits with Counterfactual Fairness
Oct 1, 2026Junhyuk Huh, Seoungbin Bae, Dabeen LeeMulti-Armed Bandits Minimax Regret
Faculty of Mathematics, University of Cambridge · Department of Industrial & Systems Engineering, KAIST · Department of Mathematical Sciences, Seoul National University
Information-Directed Sampling for Causal Bandits
Jul 17, 2026Muhammad Qasim Elahi, Murat Kocaoglu, Mahsa GhasemiThompson Sampling Multi-Armed Bandits
School of Electrical and Computer Engineering, Purdue University · School of Computer Science, Johns Hopkins University
Fixed-Confidence Best-Arm Identification for Causal Mediation Analysis
Jul 5, 2026Harsh Shrivastava, Yuta Kawakami, Junpei Komiyama +1Multi-Armed Bandits Causal Effect Estimation
Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, UAE · RIKEN AIP, Tokyo, Japan
Certified Policy Optimisation for Nested Causal Bandits via PAC-Bayes Risk
May 28, 2026Tim Woydt, Paul-David ZuercherPAC-Bayesian Generalization Bounds Multi-Armed Bandits
ProdAxon · Department of Computer Science Technical University Darmstadt · Institute for Manufacturing Department of Engineering University of Cambridge
Adaptive Policy Learning Under Unknown Network Interference
May 11, 2026Aidan Gleich, Eric Laber, Alexander VolfovskyThompson Sampling Multi-Armed Bandits
Department of Statistical Science Duke University
Budget-Constrained Causal Bandits: Bridging Uplift Modeling and Sequential Decision-Making
Apr 28, 2026Abhirami PillaiMulti-Armed Bandits Causal Effect Estimation
utdallas
The Minimal Search Space for Conditional Causal Bandits
Feb 10, 2025Francisco N. F. Q. Simoes, Itai Feigenbaum, Mehdi Dastani +1Multi-Armed Bandits Causal Bandits
Department of Computer Science, Delft University of Technology, The Netherlands · Lehman College and The Graduate Center, City University of New York, New York · Department of Information and Computing Sciences, Utrecht University, The Netherlands

Nov 6, 2026J/K move · Enter open · S save

Online Causal Configuration for Networked Systems via Doubly Robust Steady-State Learning

Yuli Liu, Zhiheng Zhang

Smart Ocean Technology, University of Macau, Macao SAR, China · School of Statistics and Data Science, Shanghai University of Finance and Economics Shanghai 200433, P.R. China · Institute of Big Data Research, Shanghai University of Finance and Economics Shanghai 200433, P.R. China

Causal Bandits Causal Inference Causal Effect Estimation Multi-Armed Bandits Doubly Robust Estimation

Open paper AskPDF arXiv

Measurement exploration reveals how interacting local controllers behave but can alter the steady-state regime a network operator seeks to optimize. Exploratory rewards may therefore fail to identify a configuration's no-exploration value: under full exploration, identical logged distributions can conceal different target values. Identification requires accounting for both action-law mismatch and shifts in the steady-state context distribution. We introduce CAUSAL-UCB, which selects configurations using optimistic bounds on target causal values. Its interference-aware clipped doubly robust evaluator produces predecision certificates separating statistical variation from calibrated identification, transport, and temporal-dependence errors. For any finite horizon and predetermined schedule of measurement-exploration rates

\{η_t\}

, we prove lower bounds of

Ω((1+\sum_tη_t)^{-1/2})

on minimax inference error and

Ω(\sum_tη_t)

on measurement-induced deployment loss in a stationary, potentially slow-mixing family. We bound regret under valid certificates and selected-information growth, and establish an anytime finite-sample certificate with a shared radius for estimation, selection, and reporting in a restricted known-local-interference model. In a high-mismatch benchmark with 24 paired seeds and 200 rounds, CAUSAL-UCB attains target regret of

1.732

versus

6.326

for certified IPS-UCB, with deployment gaps of

30.607

and

23.217

, respectively. Independent-audit coverage tests and trace-driven semi-synthetic studies further assess certificate coverage and deployment trade-offs.