{"list":"other","total":70,"rows":[{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"1708.05031","title":"Neural Collaborative Filtering","created":"2017-08-16","cited_by_count":1111},{"id":"1906.08253","title":"When to Trust Your Model: Model-Based Policy Optimization","created":"2019-06-19","cited_by_count":773},{"id":"2002.00388","title":"A Survey on Knowledge Graphs: Representation, Acquisition and Applications","created":"2020-02-02","cited_by_count":643},{"id":"2005.13239","title":"MOPO: Model-based Offline Policy Optimization","created":"2020-05-27","cited_by_count":636},{"id":"1708.06633","title":"Nonparametric regression using deep neural networks with ReLU activation function","created":"2017-08-22","cited_by_count":433},{"id":"1705.08821","title":"Causal Effect Inference with Deep Latent-Variable Models","created":"2017-05-24","cited_by_count":410},{"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":"1503.00759","title":"A Review of Relational Machine Learning for Knowledge Graphs","created":"2015-03-02","cited_by_count":265},{"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":"1712.02121","title":"A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network","created":"2017-12-06","cited_by_count":143},{"id":"1802.03493","title":"More Robust Doubly Robust Off-policy Evaluation","created":"2018-02-10","cited_by_count":141},{"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":"1805.06826","title":"The Blessings of Multiple Causes","created":"2018-05-17","cited_by_count":104},{"id":"2009.10982","title":"An Introduction to Proximal Causal Learning","created":"2020-09-23","cited_by_count":95},{"id":"1902.00450","title":"Time Series Deconfounder: Estimating Treatment Effects over Time in the Presence of Hidden Confounders","created":"2019-02-01","cited_by_count":75},{"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":"1909.03739","title":"Off-Policy Evaluation in Partially Observable Environments","created":"2019-09-09","cited_by_count":66},{"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":"2003.05623","title":"Off-policy Policy Evaluation For Sequential Decisions Under Unobserved Confounding","created":"2020-03-12","cited_by_count":61},{"id":"2002.04518","title":"Confounding-Robust Policy Evaluation in Infinite-Horizon Reinforcement Learning","created":"2020-02-11","cited_by_count":57},{"id":"1910.07186","title":"Doubly Robust Bias Reduction in Infinite Horizon Off-Policy Estimation","created":"2019-10-16","cited_by_count":48},{"id":"2104.12820","title":"Universal Off-Policy Evaluation","created":"2021-04-26","cited_by_count":43},{"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":"2110.15332","title":"Proximal Reinforcement Learning: Efficient Off-Policy Evaluation in Partially Observed Markov Decision Processes","created":"2021-10-28","cited_by_count":41},{"id":"2006.12311","title":"Provably Efficient Causal Reinforcement Learning with Confounded Observational Data","created":"2020-06-22","cited_by_count":40},{"id":"2102.03607","title":"Bootstrapping Fitted Q-Evaluation for Off-Policy Inference","created":"2021-02-06","cited_by_count":40},{"id":"1812.10576","title":"Deconfounding Reinforcement Learning in Observational Settings","created":"2018-12-26","cited_by_count":36},{"id":"2105.04646","title":"Deeply-Debiased Off-Policy Interval Estimation","created":"2021-05-10","cited_by_count":36},{"id":"2111.06784","title":"A Minimax Learning Approach to Off-Policy Evaluation in Confounded Partially Observable Markov Decision Processes","created":"2021-11-12","cited_by_count":36},{"id":"2102.09907","title":"Instrumental Variable Value Iteration for Causal Offline Reinforcement Learning","created":"2021-02-19","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":"1906.01624","title":"Off-Policy Evaluation via Off-Policy Classification","created":"2019-06-04","cited_by_count":32},{"id":"1902.04114","title":"Using Embeddings to Correct for Unobserved Confounding in Networks","created":"2019-02-11","cited_by_count":31},{"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":"2102.06648","title":"A Critical Look at the Consistency of Causal Estimation With Deep Latent Variable Models","created":"2021-02-12","cited_by_count":29},{"id":"1906.04328","title":"Importance Resampling for Off-policy Prediction","created":"2019-06-11","cited_by_count":26},{"id":"2205.13589","title":"Pessimism in the Face of Confounders: Provably Efficient Offline Reinforcement Learning in Partially Observable Markov Decision Processes","created":"2022-05-26","cited_by_count":26},{"id":"2104.09323","title":"Sequential Deconfounding for Causal Inference with Unobserved Confounders","created":"2021-04-16","cited_by_count":24},{"id":"2105.10148","title":"On Instrumental Variable Regression for Deep Offline Policy Evaluation","created":"2021-05-21","cited_by_count":22},{"id":"2109.10502","title":"A Spectral Approach to Off-Policy Evaluation for POMDPs","created":"2021-09-22","cited_by_count":21},{"id":"2212.14468","title":"An Instrumental Variable Approach to Confounded Off-Policy Evaluation","created":"2022-12-29","cited_by_count":20},{"id":"1808.06581","title":"The Deconfounded Recommender: A Causal Inference Approach to Recommendation","created":"2018-08-20","cited_by_count":19},{"id":"2209.08666","title":"Offline Reinforcement Learning with Instrumental Variables in Confounded Markov Decision Processes","created":"2022-09-18","cited_by_count":19},{"id":"2209.10064","title":"Off-Policy Evaluation for Episodic Partially Observable Markov Decision Processes under Non-Parametric Models","created":"2022-09-21","cited_by_count":18},{"id":"1910.05438","title":"Comment on \"Blessings of Multiple Causes\"","created":"2019-10-11","cited_by_count":16},{"id":"1808.05293","title":"Design-based Analysis in Difference-In-Differences Settings with Staggered Adoption","created":"2018-08-15","cited_by_count":15},{"id":"2202.06891","title":"Counterfactual inference in sequential experiments","created":"2022-02-14","cited_by_count":13},{"id":"2302.00662","title":"Robust Fitted-Q-Evaluation and Iteration under Sequentially Exogenous Unobserved Confounders","created":"2023-02-01","cited_by_count":13},{"id":"2211.09403","title":"Learning Mixtures of Markov Chains and MDPs","created":"2022-11-17","cited_by_count":12},{"id":"2211.16583","title":"Offline Policy Evaluation and Optimization under Confounding","created":"2022-11-29","cited_by_count":12},{"id":"1710.10742","title":"Implicit Causal Models for Genome-wide Association Studies","created":"2017-10-30","cited_by_count":10},{"id":"2211.08209","title":"On counterfactual inference with unobserved confounding","created":"2022-11-14","cited_by_count":10},{"id":"2208.11040","title":"Strategic Decision-Making in the Presence of Information Asymmetry: Provably Efficient RL with Algorithmic Instruments","created":"2022-08-23","cited_by_count":9},{"id":"1607.06565","title":"Estimating Causal Peer Influence in Homophilous Social Networks by Inferring Latent Locations","created":"2016-07-22","cited_by_count":8},{"id":"2001.06555","title":"Counterexamples to \"The Blessings of Multiple Causes\" by Wang and Blei","created":"2020-01-17","cited_by_count":8},{"id":"2210.14420","title":"Optimizing Pessimism in Dynamic Treatment Regimes: A Bayesian Learning Approach","created":"2022-10-26","cited_by_count":7},{"id":"2306.08719","title":"Off-policy Evaluation in Doubly Inhomogeneous Environments","created":"2023-06-14","cited_by_count":7},{"id":"1910.08042","title":"Comment: Reflections on the Deconfounder","created":"2019-10-17","cited_by_count":6},{"id":"2305.17083","title":"A Policy Gradient Method for Confounded POMDPs","created":"2023-05-26","cited_by_count":6},{"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":"2311.16793","title":"Mediation analysis with unmeasured confounding between parallel mediators and outcome","created":"2023-11-28","cited_by_count":1}],"next_cursor":null}