{"list":"other","total":51,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"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":"1503.02834","title":"Doubly Robust Policy Evaluation and Optimization","created":"2015-03-10","cited_by_count":158},{"id":"1910.12809","title":"Minimax Weight and Q-Function Learning for Off-Policy Evaluation","created":"2019-10-28","cited_by_count":150},{"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":"1911.02768","title":"Confidence Intervals for Policy Evaluation in Adaptive Experiments","created":"2019-11-07","cited_by_count":95},{"id":"2212.06355","title":"A Review of Off-Policy Evaluation in Reinforcement Learning","created":"2022-12-13","cited_by_count":95},{"id":"2204.05275","title":"Settling the Sample Complexity of Model-Based Offline Reinforcement Learning","created":"2022-04-11","cited_by_count":83},{"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":"1909.03539","title":"Personalized HeartSteps: A Reinforcement Learning Algorithm for Optimizing Physical Activity","created":"2019-09-08","cited_by_count":70},{"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":"2002.03217","title":"Inference for Batched Bandits","created":"2020-02-08","cited_by_count":63},{"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":"1907.04068","title":"Conditional Independence Testing using Generative Adversarial Networks","created":"2019-07-09","cited_by_count":36},{"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":"2106.00418","title":"Post-Contextual-Bandit Inference","created":"2021-06-01","cited_by_count":32},{"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":"2108.03706","title":"Online Bootstrap Inference For Policy Evaluation in Reinforcement Learning","created":"2021-08-08","cited_by_count":26},{"id":"2110.10719","title":"Estimating Optimal Infinite Horizon Dynamic Treatment Regimes via pT-Learning","created":"2021-10-20","cited_by_count":26},{"id":"2011.02258","title":"Concentration Inequalities for Statistical Inference","created":"2020-11-04","cited_by_count":24},{"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":"2006.02615","title":"Double Generative Adversarial Networks for Conditional Independence Testing","created":"2020-06-03","cited_by_count":22},{"id":"2102.13202","title":"Online Multi-Armed Bandits with Adaptive Inference","created":"2021-02-25","cited_by_count":22},{"id":"2206.02371","title":"Markovian Interference in Experiments","created":"2022-06-06","cited_by_count":22},{"id":"2105.09452","title":"Minimum-Delay Adaptation in Non-Stationary Reinforcement Learning via Online High-Confidence Change-Point Detection","created":"2021-05-20","cited_by_count":18},{"id":"2109.04640","title":"Projected State-action Balancing Weights for Offline Reinforcement Learning","created":"2021-09-10","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":"2203.01707","title":"Testing Stationarity and Change Point Detection in Reinforcement Learning","created":"2022-03-03","cited_by_count":12},{"id":"2306.07024","title":"DRCFS: Doubly Robust Causal Feature Selection","created":"2023-06-12","cited_by_count":12},{"id":"2311.02532","title":"Optimal Treatment Allocation for Efficient Policy Evaluation in Sequential Decision Making","created":"2023-11-05","cited_by_count":11},{"id":"2202.13163","title":"Statistically Efficient Advantage Learning for Offline Reinforcement Learning in Infinite Horizons","created":"2022-02-26","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":"2404.09946","title":"A Note on Loss Functions and Error Compounding in Model-based Reinforcement Learning","created":"2024-04-15","cited_by_count":8},{"id":"2407.17694","title":"Doubly Robust Conditional Independence Testing with Generative Neural Networks","created":"2024-07-25","cited_by_count":7},{"id":"2309.13278","title":"Distributional Shift-Aware Off-Policy Interval Estimation: A Unified Error Quantification Framework","created":"2023-09-23","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":"2106.01474","title":"Testing Directed Acyclic Graph via Structural, Supervised and Generative Adversarial Learning","created":"2021-06-02","cited_by_count":4},{"id":"2501.17345","title":"Testing Conditional Mean Independence Using Generative Neural Networks","created":"2025-01-28","cited_by_count":3},{"id":"2409.14684","title":"Consistent Order Determination of Markov Decision Process","created":"2024-09-23","cited_by_count":1}],"next_cursor":null}