{"list":"other","total":71,"rows":[{"id":"1511.03722","title":"Doubly Robust Off-policy Value Evaluation for Reinforcement Learning","created":"2015-11-11","cited_by_count":339},{"id":"1604.00923","title":"Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning","created":"2016-04-04","cited_by_count":286},{"id":"1903.08738","title":"Batch Policy Learning under Constraints","created":"2019-03-20","cited_by_count":244},{"id":"1810.12429","title":"Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation","created":"2018-10-29","cited_by_count":227},{"id":"2103.02438","title":"Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Design","created":"2021-03-03","cited_by_count":106},{"id":"1909.05850","title":"Efficiently Breaking the Curse of Horizon in Off-Policy Evaluation with Double Reinforcement Learning","created":"2019-09-12","cited_by_count":75},{"id":"2007.11771","title":"Batch Policy Learning in Average Reward Markov Decision Processes","created":"2020-07-23","cited_by_count":69},{"id":"1611.03531","title":"Estimating Dynamic Treatment Regimes in Mobile Health Using V-learning","created":"2016-11-10","cited_by_count":65},{"id":"2001.04515","title":"Statistical Inference of the Value Function for Reinforcement Learning in Infinite Horizon Settings","created":"2020-01-13","cited_by_count":65},{"id":"2010.11652","title":"CoinDICE: Off-Policy Confidence Interval Estimation","created":"2020-10-22","cited_by_count":64},{"id":"2202.00821","title":"Optimizing Sequential Experimental Design with Deep Reinforcement Learning","created":"2022-02-02","cited_by_count":46},{"id":"2106.04493","title":"A Deep Value-network Based Approach for Multi-Driver Order Dispatching","created":"2021-06-08","cited_by_count":45},{"id":"1609.06245","title":"Identification and estimation of treatment and interference effects in observational studies on networks","created":"2016-09-20","cited_by_count":44},{"id":"1305.6979","title":"Graph cluster randomization: network exposure to multiple universes","created":"2013-05-30","cited_by_count":42},{"id":"2102.03607","title":"Bootstrapping Fitted Q-Evaluation for Off-Policy Inference","created":"2021-02-06","cited_by_count":40},{"id":"2002.08506","title":"Causal Inference under Networked Interference and Intervention Policy Enhancement","created":"2020-02-20","cited_by_count":38},{"id":"2006.10460","title":"Confident Off-Policy Evaluation and Selection through Self-Normalized Importance Weighting","created":"2020-06-18","cited_by_count":38},{"id":"2009.00148","title":"Design and Analysis of Switchback Experiments","created":"2020-08-31","cited_by_count":38},{"id":"2008.06668","title":"Accountable Off-Policy Evaluation With Kernel Bellman Statistics","created":"2020-08-15","cited_by_count":36},{"id":"2105.04646","title":"Deeply-Debiased Off-Policy Interval Estimation","created":"2021-05-10","cited_by_count":36},{"id":"1802.08667","title":"De-Biased Machine Learning of Global and Local Parameters Using Regularized Riesz Representers","created":"2018-02-23","cited_by_count":34},{"id":"2201.06169","title":"On Well-posedness and Minimax Optimal Rates of Nonparametric Q-function Estimation in Off-policy Evaluation","created":"2022-01-17","cited_by_count":33},{"id":"2202.10589","title":"Off-Policy Confidence Interval Estimation with Confounded Markov Decision Process","created":"2022-02-22","cited_by_count":31},{"id":"2002.01711","title":"Dynamic Causal Effects Evaluation in A/B Testing with a Reinforcement Learning Framework","created":"2020-02-05","cited_by_count":29},{"id":"1907.00221","title":"Causal Inference Under Interference And Network Uncertainty","created":"2019-06-29","cited_by_count":27},{"id":"1706.03469","title":"Data-Efficient Policy Evaluation Through Behavior Policy Search","created":"2017-06-12","cited_by_count":26},{"id":"2110.12343","title":"Off-Policy Evaluation in Partially Observed Markov Decision Processes under Sequential Ignorability","created":"2021-10-24","cited_by_count":24},{"id":"2104.12222","title":"Interference, Bias, and Variance in Two-Sided Marketplace Experimentation: Guidance for Platforms","created":"2021-04-25","cited_by_count":22},{"id":"2206.02371","title":"Markovian Interference in Experiments","created":"2022-06-06","cited_by_count":22},{"id":"2112.13495","title":"Multiple Randomization Designs: Estimation and Inference with Interference","created":"2021-12-27","cited_by_count":20},{"id":"2212.14468","title":"An Instrumental Variable Approach to Confounded Off-Policy Evaluation","created":"2022-12-29","cited_by_count":20},{"id":"2209.00197","title":"Switchback Experiments under Geometric Mixing","created":"2022-09-01","cited_by_count":17},{"id":"1903.02124","title":"Experimenting in Equilibrium","created":"2019-03-06","cited_by_count":16},{"id":"2109.04640","title":"Projected State-action Balancing Weights for Offline Reinforcement Learning","created":"2021-09-10","cited_by_count":16},{"id":"2109.11647","title":"Treatment Effects in Market Equilibrium","created":"2021-09-23","cited_by_count":16},{"id":"1807.08660","title":"Bipartite Causal Inference with Interference","created":"2018-07-23","cited_by_count":15},{"id":"2111.14552","title":"Robust On-Policy Sampling for Data-Efficient Policy Evaluation in Reinforcement Learning","created":"2021-11-29","cited_by_count":15},{"id":"2202.13234","title":"Safe Exploration for Efficient Policy Evaluation and Comparison","created":"2022-02-26","cited_by_count":15},{"id":"2111.04219","title":"Rate-Optimal Cluster-Randomized Designs for Spatial Interference","created":"2021-11-08","cited_by_count":14},{"id":"2301.13734","title":"Efficient Policy Evaluation with Offline Data Informed Behavior Policy Design","created":"2023-01-31","cited_by_count":14},{"id":"1911.03071","title":"Balancing Covariates in Randomized Experiments with the Gram-Schmidt Walk Design","created":"2019-11-08","cited_by_count":13},{"id":"2007.02714","title":"A review of spatial causal inference methods for environmental and epidemiological applications","created":"2020-07-06","cited_by_count":12},{"id":"2403.03589","title":"Active Adaptive Experimental Design for Treatment Effect Estimation with Covariate Choices","created":"2024-03-06","cited_by_count":12},{"id":"2406.06768","title":"Data-Driven Switchback Experiments: Theoretical Tradeoffs and Empirical Bayes Designs","created":"2024-06-10","cited_by_count":12},{"id":"2104.03802","title":"Average Direct and Indirect Causal Effects under Interference","created":"2021-04-08","cited_by_count":10},{"id":"2310.14983","title":"Causal clustering: design of cluster experiments under network interference","created":"2023-10-23","cited_by_count":10},{"id":"2402.01845","title":"Multi-Armed Bandits with Interference","created":"2024-02-02","cited_by_count":10},{"id":"2412.03727","title":"Online Experimental Design With Estimation-Regret Trade-off Under Network Interference","created":"2024-12-04","cited_by_count":9},{"id":"2004.07225","title":"Minimizing Interference and Selection Bias in Network Experiment Design","created":"2020-04-15","cited_by_count":8},{"id":"2012.08591","title":"Network experimentation at scale","created":"2020-12-15","cited_by_count":8},{"id":"2202.10887","title":"Policy Evaluation for Temporal and/or Spatial Dependent Experiments","created":"2022-02-22","cited_by_count":8},{"id":"2405.18621","title":"Multi-Armed Bandits with Network Interference","created":"2024-05-28","cited_by_count":8},{"id":"2409.15682","title":"Linear Contextual Bandits with Interference","created":"2024-09-24","cited_by_count":8},{"id":"1910.10862","title":"A Graph-Theoretic Approach to Randomization Tests of Causal Effects Under General Interference","created":"2019-10-24","cited_by_count":7},{"id":"2211.07823","title":"Graph Neural Networks for Causal Inference Under Network Confounding","created":"2022-11-15","cited_by_count":7},{"id":"2305.10187","title":"Evaluating Dynamic Conditional Quantile Treatment Effects with Applications in Ridesharing","created":"2023-05-17","cited_by_count":7},{"id":"2306.08719","title":"Off-policy Evaluation in Doubly Inhomogeneous Environments","created":"2023-06-14","cited_by_count":7},{"id":"2008.08648","title":"Cluster-Adaptive Network A/B Testing: From Randomization to Estimation","created":"2020-08-19","cited_by_count":6},{"id":"2403.17285","title":"Unraveling the Interplay between Carryover Effects and Reward Autocorrelations in Switchback Experiments","created":"2024-03-26","cited_by_count":6},{"id":"2408.09607","title":"Experimental Design For Causal Inference Through An Optimization Lens","created":"2024-08-18","cited_by_count":6},{"id":"1806.07422","title":"Doubly Robust Estimation in Observational Studies with Partial Interference","created":"2018-06-19","cited_by_count":5},{"id":"2309.00141","title":"Causal Inference under Network Interference Using a Mixture of Randomized Experiments","created":"2023-08-31","cited_by_count":4},{"id":"2402.10870","title":"Best of Three Worlds: Adaptive Experimentation for Digital Marketing in Practice","created":"2024-02-16","cited_by_count":4},{"id":"2311.14042","title":"Optimized Covariance Design for AB Test on Social Network under Interference","created":"2023-11-23","cited_by_count":3},{"id":"2404.04775","title":"Bipartite causal inference with interference, time series data, and a random network","created":"2024-04-07","cited_by_count":3},{"id":"2406.14380","title":"Estimating Treatment Effects under Algorithmic Interference: A Structured Neural Networks Approach","created":"2024-06-20","cited_by_count":3},{"id":"2401.15811","title":"Seller-Side Experiments under Interference Induced by Feedback Loops in Two-Sided Platforms","created":"2024-01-29","cited_by_count":2},{"id":"2405.07979","title":"Low-order outcomes and clustered designs: combining design and analysis for causal inference under network interference","created":"2024-05-13","cited_by_count":2},{"id":"2407.17910","title":"Causal Deepsets for Off-policy Evaluation under Spatial or Spatio-temporal Interferences","created":"2024-07-25","cited_by_count":2},{"id":"2408.04441","title":"Causal Inference in Social Platforms Under Approximate Interference Networks","created":"2024-08-08","cited_by_count":1},{"id":"2409.04836","title":"Spatial Interference Detection in Treatment Effect Model","created":"2024-09-07","cited_by_count":1}],"next_cursor":null}