{"list":"other","total":73,"rows":[{"id":"1907.05388","title":"Provably Efficient Reinforcement Learning with Linear Function Approximation","created":"2019-07-11","cited_by_count":520},{"id":"1511.03722","title":"Doubly Robust Off-policy Value Evaluation for Reinforcement Learning","created":"2015-11-11","cited_by_count":339},{"id":"1905.00360","title":"Information-Theoretic Considerations in Batch Reinforcement Learning","created":"2019-05-01","cited_by_count":287},{"id":"1604.00923","title":"Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning","created":"2016-04-04","cited_by_count":286},{"id":"1906.04733","title":"DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Corrections","created":"2019-06-10","cited_by_count":254},{"id":"1810.12429","title":"Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation","created":"2018-10-29","cited_by_count":227},{"id":"1901.00137","title":"A Theoretical Analysis of Deep Q-Learning","created":"2019-01-01","cited_by_count":215},{"id":"1910.12809","title":"Minimax Weight and Q-Function Learning for Off-Policy Evaluation","created":"2019-10-28","cited_by_count":150},{"id":"1906.03393","title":"Towards Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling","created":"2019-06-08","cited_by_count":119},{"id":"1908.08526","title":"Double Reinforcement Learning for Efficient Off-Policy Evaluation in Markov Decision Processes","created":"2019-08-22","cited_by_count":119},{"id":"2103.02438","title":"Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Design","created":"2021-03-03","cited_by_count":106},{"id":"2212.06355","title":"A Review of Off-Policy Evaluation in Reinforcement Learning","created":"2022-12-13","cited_by_count":95},{"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":"2001.10742","title":"Asymptotically Efficient Off-Policy Evaluation for Tabular Reinforcement Learning","created":"2020-01-29","cited_by_count":60},{"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":"1305.6979","title":"Graph cluster randomization: network exposure to multiple universes","created":"2013-05-30","cited_by_count":42},{"id":"1912.13088","title":"Off-Policy Estimation of Long-Term Average Outcomes with Applications to Mobile Health","created":"2019-12-30","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":"2002.05670","title":"Experimental Design in Two-Sided Platforms: An Analysis of Bias","created":"2020-02-13","cited_by_count":39},{"id":"2009.00148","title":"Design and Analysis of Switchback Experiments","created":"2020-08-31","cited_by_count":38},{"id":"2210.10768","title":"Anytime-valid off-policy inference for contextual bandits","created":"2022-10-19","cited_by_count":37},{"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":"2002.01751","title":"Does the Markov Decision Process Fit the Data: Testing for the Markov Property in Sequential Decision Making","created":"2020-02-05","cited_by_count":30},{"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":"2105.08024","title":"Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting","created":"2021-05-17","cited_by_count":28},{"id":"1601.00237","title":"Assessing Time-Varying Causal Effect Moderation in Mobile Health","created":"2016-01-03","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":"1706.07840","title":"Time series experiments and causal estimands: exact randomization tests and trading","created":"2017-06-23","cited_by_count":21},{"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":"1905.05787","title":"Combining Parametric and Nonparametric Models for Off-Policy Evaluation","created":"2019-05-14","cited_by_count":17},{"id":"1912.06292","title":"More Efficient Off-Policy Evaluation through Regularized Targeted Learning","created":"2019-12-13","cited_by_count":17},{"id":"2209.00197","title":"Switchback Experiments under Geometric Mixing","created":"2022-09-01","cited_by_count":17},{"id":"1709.01577","title":"Auto-G-Computation of Causal Effects on a Network","created":"2017-09-05","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":"2203.04272","title":"Policy-Based Bayesian Experimental Design for Non-Differentiable Implicit Models","created":"2022-03-08","cited_by_count":16},{"id":"2203.04510","title":"ReVar: Strengthening Policy Evaluation via Reduced Variance Sampling","created":"2022-03-09","cited_by_count":16},{"id":"2308.04929","title":"A/B Testing: A Systematic Literature Review","created":"2023-08-09","cited_by_count":16},{"id":"2006.05591","title":"Adaptive Experimental Design with Temporal Interference: A Maximum Likelihood Approach","created":"2020-06-10","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":"2007.02714","title":"A review of spatial causal inference methods for environmental and epidemiological applications","created":"2020-07-06","cited_by_count":12},{"id":"2305.02542","title":"Correcting for Interference in Experiments: A Case Study at Douyin","created":"2023-05-04","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":"2102.05805","title":"Graph-Based Equilibrium Metrics for Dynamic Supply-Demand Systems with Applications to Ride-sourcing Platforms","created":"2021-02-11","cited_by_count":11},{"id":"2311.02532","title":"Optimal Treatment Allocation for Efficient Policy Evaluation in Sequential Decision Making","created":"2023-11-05","cited_by_count":11},{"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":"2305.19244","title":"Testing for the Markov Property in Time Series via Deep Conditional Generative Learning","created":"2023-05-30","cited_by_count":9},{"id":"2202.10887","title":"Policy Evaluation for Temporal and/or Spatial Dependent Experiments","created":"2022-02-22","cited_by_count":8},{"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":"2311.08340","title":"Causal Message Passing for Experiments with Unknown and General Network Interference","created":"2023-11-14","cited_by_count":7},{"id":"2105.10821","title":"Statistical Testing under Distributional Shifts","created":"2021-05-22","cited_by_count":6},{"id":"1605.09171","title":"Randomization and The Pernicious Effects of Limited Budgets on Auction Experiments","created":"2016-05-30","cited_by_count":5},{"id":"1904.01490","title":"Synthetic learner: model-free inference on treatments over time","created":"2019-04-02","cited_by_count":5},{"id":"2011.00373","title":"Causal Inference for Spatial Treatments","created":"2020-10-31","cited_by_count":5},{"id":"2210.07536","title":"A Reinforcement Learning Approach to Estimating Long-term Treatment Effects","created":"2022-10-14","cited_by_count":5},{"id":"2310.16989","title":"Randomization Inference When N Equals One","created":"2023-10-25","cited_by_count":5},{"id":"1807.01635","title":"Randomization Inference for Peer Effects","created":"2018-07-04","cited_by_count":4},{"id":"2310.02581","title":"Online Estimation and Inference for Robust Policy Evaluation in Reinforcement Learning","created":"2023-10-04","cited_by_count":4}],"next_cursor":null}