{"list":"other","total":56,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2012.07436","title":"Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting","created":"2020-12-14","cited_by_count":2169},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"2011.00931","title":"Point Transformer","created":"2020-11-02","cited_by_count":1470},{"id":"1703.06114","title":"Deep Sets","created":"2017-03-10","cited_by_count":1421},{"id":"1611.08097","title":"Geometric deep learning: going beyond Euclidean data","created":"2016-11-24","cited_by_count":1048},{"id":"1610.01145","title":"Error bounds for approximations with deep ReLU networks","created":"2016-10-03","cited_by_count":574},{"id":"1708.06633","title":"Nonparametric regression using deep neural networks with ReLU activation function","created":"2017-08-22","cited_by_count":433},{"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":"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":"1901.00137","title":"A Theoretical Analysis of Deep Q-Learning","created":"2019-01-01","cited_by_count":215},{"id":"1802.05438","title":"Mean Field Multi-Agent Reinforcement Learning","created":"2018-02-15","cited_by_count":207},{"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":"2008.04990","title":"Batch Value-function Approximation with Only Realizability","created":"2020-08-11","cited_by_count":104},{"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":"1909.03739","title":"Off-Policy Evaluation in Partially Observable Environments","created":"2019-09-09","cited_by_count":66},{"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":"2001.10742","title":"Asymptotically Efficient Off-Policy Evaluation for Tabular Reinforcement Learning","created":"2020-01-29","cited_by_count":60},{"id":"1802.04474","title":"Deep Neural Networks Learn Non-Smooth Functions Effectively","created":"2018-02-13","cited_by_count":57},{"id":"2002.04518","title":"Confounding-Robust Policy Evaluation in Infinite-Horizon Reinforcement Learning","created":"2020-02-11","cited_by_count":57},{"id":"2301.03044","title":"A Survey on Transformers in Reinforcement Learning","created":"2023-01-08","cited_by_count":50},{"id":"1910.07186","title":"Doubly Robust Bias Reduction in Infinite Horizon Off-Policy Estimation","created":"2019-10-16","cited_by_count":48},{"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":"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":"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":"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":"2112.11666","title":"Local permutation tests for conditional independence","created":"2021-12-22","cited_by_count":23},{"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":"1903.02124","title":"Experimenting in Equilibrium","created":"2019-03-06","cited_by_count":16},{"id":"2109.11647","title":"Treatment Effects in Market Equilibrium","created":"2021-09-23","cited_by_count":16},{"id":"2111.04219","title":"Rate-Optimal Cluster-Randomized Designs for Spatial Interference","created":"2021-11-08","cited_by_count":14},{"id":"2010.13055","title":"Regularizing Towards Permutation Invariance in Recurrent Models","created":"2020-10-25","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":"2007.02714","title":"A review of spatial causal inference methods for environmental and epidemiological applications","created":"2020-07-06","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":"1909.12903","title":"PINE: Universal Deep Embedding for Graph Nodes via Partial Permutation Invariant Set Functions","created":"2019-09-25","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":"1610.07583","title":"Adjusting for Unmeasured Spatial Confounding with Distance Adjusted Propensity Score Matching","created":"2016-10-24","cited_by_count":7},{"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":"2307.02520","title":"Conditional independence testing under misspecified inductive biases","created":"2023-07-05","cited_by_count":7},{"id":"1807.01635","title":"Randomization Inference for Peer Effects","created":"2018-07-04","cited_by_count":4},{"id":"2103.00304","title":"Instrumental variables, spatial confounding and interference","created":"2021-02-27","cited_by_count":3},{"id":"1909.11161","title":"Selecting a Scale for Spatial Confounding Adjustment","created":"2019-09-24","cited_by_count":2}],"next_cursor":null}