{"list":"other","total":68,"rows":[{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"1906.00949","title":"Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction","created":"2019-06-03","cited_by_count":840},{"id":"2012.15085","title":"Is Pessimism Provably Efficient for Offline RL?","created":"2020-12-30","cited_by_count":364},{"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":"2103.12021","title":"Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism","created":"2021-03-22","cited_by_count":279},{"id":"2106.06926","title":"Bellman-consistent Pessimism for Offline Reinforcement Learning","created":"2021-06-13","cited_by_count":269},{"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":"2107.06226","title":"Pessimistic Model-based Offline Reinforcement Learning under Partial Coverage","created":"2021-07-13","cited_by_count":164},{"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":"1802.03493","title":"More Robust Doubly Robust Off-policy Evaluation","created":"2018-02-10","cited_by_count":141},{"id":"2202.11566","title":"Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning","created":"2022-02-23","cited_by_count":125},{"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":"2204.12581","title":"RAMBO-RL: Robust Adversarial Model-Based Offline Reinforcement Learning","created":"2022-04-26","cited_by_count":115},{"id":"2009.06799","title":"The Importance of Pessimism in Fixed-Dataset Policy Optimization","created":"2020-09-15","cited_by_count":99},{"id":"2212.06355","title":"A Review of Off-Policy Evaluation in Reinforcement Learning","created":"2022-12-13","cited_by_count":95},{"id":"2202.13890","title":"Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity","created":"2022-02-28","cited_by_count":85},{"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":"2203.05804","title":"Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism","created":"2022-03-11","cited_by_count":65},{"id":"1810.11646","title":"Removing Hidden Confounding by Experimental Grounding","created":"2018-10-27","cited_by_count":64},{"id":"2010.11652","title":"CoinDICE: Off-Policy Confidence Interval Estimation","created":"2020-10-22","cited_by_count":64},{"id":"1806.03467","title":"Orthogonal Random Forest for Causal Inference","created":"2018-06-09","cited_by_count":51},{"id":"2011.08047","title":"Causal inference methods for combining randomized trials and observational studies: a review","created":"2020-11-16","cited_by_count":51},{"id":"2106.04493","title":"A Deep Value-network Based Approach for Multi-Driver Order Dispatching","created":"2021-06-08","cited_by_count":45},{"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":"2009.00148","title":"Design and Analysis of Switchback Experiments","created":"2020-08-31","cited_by_count":38},{"id":"2102.11904","title":"A Review of Generalizability and Transportability","created":"2021-02-23","cited_by_count":37},{"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":"2105.01099","title":"Reinforcement Learning for Ridesharing: An Extended Survey","created":"2021-05-03","cited_by_count":35},{"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":"2106.00418","title":"Post-Contextual-Bandit Inference","created":"2021-06-01","cited_by_count":32},{"id":"2212.09900","title":"Policy learning \"without\" overlap: Pessimism and generalized empirical Bernstein's inequality","created":"2022-12-19","cited_by_count":32},{"id":"1801.00802","title":"Combining multiple observational data sources to estimate causal effects","created":"2018-01-02","cited_by_count":29},{"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":"1704.00211","title":"Nonparametric causal effects based on incremental propensity score interventions","created":"2017-04-01","cited_by_count":28},{"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":"2111.15012","title":"Adaptive Combination of Randomized and Observational Data","created":"2021-11-29","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":"2207.13081","title":"Future-Dependent Value-Based Off-Policy Evaluation in POMDPs","created":"2022-07-26","cited_by_count":21},{"id":"2109.04640","title":"Projected State-action Balancing Weights for Offline Reinforcement Learning","created":"2021-09-10","cited_by_count":16},{"id":"2112.09313","title":"Federated Adaptive Causal Estimation (FACE) of Target Treatment Effects","created":"2021-12-17","cited_by_count":16},{"id":"2309.12600","title":"Multiply Robust Federated Estimation of Targeted Average Treatment Effects","created":"2023-09-22","cited_by_count":13},{"id":"2203.01707","title":"Testing Stationarity and Change Point Detection in Reinforcement Learning","created":"2022-03-03","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":"2110.01106","title":"Data Integration in Causal Inference","created":"2021-10-03","cited_by_count":11},{"id":"1908.09230","title":"Efficient and robust methods for causally interpretable meta-analysis: transporting inferences from multiple randomized trials to a target population","created":"2019-08-24","cited_by_count":10},{"id":"2011.07234","title":"Improving efficiency of inference in clinical trials with external control data","created":"2020-11-14","cited_by_count":10},{"id":"1611.02385","title":"Combining observational and experimental data to find heterogeneous treatment effects","created":"2016-11-08","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":"2003.01242","title":"Improving trial generalizability using observational studies","created":"2020-03-02","cited_by_count":7},{"id":"2210.14420","title":"Optimizing Pessimism in Dynamic Treatment Regimes: A Bayesian Learning Approach","created":"2022-10-26","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":"2307.04304","title":"Enhancing Treatment Effect Estimation: A Model Robust Approach Integrating Randomized Experiments and External Controls using the Double Penalty Integration Estimator","created":"2023-07-10","cited_by_count":6},{"id":"2310.06969","title":"Positivity-free Policy Learning with Observational Data","created":"2023-10-10","cited_by_count":6},{"id":"2210.07536","title":"A Reinforcement Learning Approach to Estimating Long-term Treatment Effects","created":"2022-10-14","cited_by_count":5},{"id":"2310.06268","title":"Bi-Level Offline Policy Optimization with Limited Exploration","created":"2023-10-10","cited_by_count":5},{"id":"2105.13218","title":"Pattern Transfer Learning for Reinforcement Learning in Order Dispatching","created":"2021-05-27","cited_by_count":4},{"id":"2302.07840","title":"Causally-interpretable meta-analysis: clearly-defined causal effects and two case studies","created":"2023-02-15","cited_by_count":1},{"id":"2401.06082","title":"Borrowing from historical control data in a Bayesian time-to-event model with flexible baseline hazard function","created":"2024-01-11","cited_by_count":1}],"next_cursor":null}