{"list":"other","total":91,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"2205.13504","title":"Are Transformers Effective for Time Series Forecasting?","created":"2022-05-26","cited_by_count":1424},{"id":"1803.08475","title":"Attention, Learn to Solve Routing Problems!","created":"2018-03-22","cited_by_count":656},{"id":"1611.09940","title":"Neural Combinatorial Optimization with Reinforcement Learning","created":"2016-11-29","cited_by_count":608},{"id":"1511.03722","title":"Doubly Robust Off-policy Value Evaluation for Reinforcement Learning","created":"2015-11-11","cited_by_count":339},{"id":"1903.08738","title":"Batch Policy Learning under Constraints","created":"2019-03-20","cited_by_count":244},{"id":"2003.03600","title":"Reinforcement Learning for Combinatorial Optimization: A Survey","created":"2020-03-07","cited_by_count":236},{"id":"1810.12429","title":"Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation","created":"2018-10-29","cited_by_count":227},{"id":"1906.04477","title":"Causal Discovery with Reinforcement Learning","created":"2019-06-11","cited_by_count":145},{"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":"1706.04972","title":"Device Placement Optimization with Reinforcement Learning","created":"2017-06-13","cited_by_count":86},{"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":"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":"1804.11147","title":"FIRST: A Framework for Optimizing Information Quality in Mobile Crowdsensing Systems","created":"2018-04-30","cited_by_count":50},{"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":"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":"2105.04646","title":"Deeply-Debiased Off-Policy Interval Estimation","created":"2021-05-10","cited_by_count":36},{"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":"2002.01711","title":"Dynamic Causal Effects Evaluation in A/B Testing with a Reinforcement Learning Framework","created":"2020-02-05","cited_by_count":29},{"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":"2103.04555","title":"Real-world Ride-hailing Vehicle Repositioning using Deep Reinforcement Learning","created":"2021-03-08","cited_by_count":22},{"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":"2410.02504","title":"Dual Active Learning for Reinforcement Learning from Human Feedback","created":"2024-10-03","cited_by_count":20},{"id":"1706.05378","title":"A framework for Multi-A(rmed)/B(andit) testing with online FDR control","created":"2017-06-16","cited_by_count":17},{"id":"2209.00197","title":"Switchback Experiments under Geometric Mixing","created":"2022-09-01","cited_by_count":17},{"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":"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":"2301.13734","title":"Efficient Policy Evaluation with Offline Data Informed Behavior Policy Design","created":"2023-01-31","cited_by_count":14},{"id":"1911.03764","title":"Optimal Experimental Design for Staggered Rollouts","created":"2019-11-09","cited_by_count":13},{"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":"2406.06768","title":"Data-Driven Switchback Experiments: Theoretical Tradeoffs and Empirical Bayes Designs","created":"2024-06-10","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":"2005.00564","title":"Response-adaptive randomization in clinical trials: from myths to practical considerations","created":"2020-05-01","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":"2310.14983","title":"Causal clustering: design of cluster experiments under network interference","created":"2023-10-23","cited_by_count":10},{"id":"2003.08421","title":"Experimental Design under Network Interference","created":"2020-03-18","cited_by_count":9},{"id":"2412.03727","title":"Online Experimental Design With Estimation-Regret Trade-off Under Network Interference","created":"2024-12-04","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":"2410.02226","title":"Doubly Optimal Policy Evaluation for Reinforcement Learning","created":"2024-10-03","cited_by_count":8},{"id":"2202.05356","title":"Network Interference in Micro-Randomized Trials","created":"2022-02-10","cited_by_count":7},{"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":"2008.08648","title":"Cluster-Adaptive Network A/B Testing: From Randomization to Estimation","created":"2020-08-19","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":"2406.00317","title":"Combining Experimental and Historical Data for Policy Evaluation","created":"2024-06-01","cited_by_count":6},{"id":"2408.09607","title":"Experimental Design For Causal Inference Through An Optimization Lens","created":"2024-08-18","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":"2310.16989","title":"Randomization Inference When N Equals One","created":"2023-10-25","cited_by_count":5},{"id":"2505.20130","title":"Balancing Interference and Correlation in Spatial Experimental Designs: A Causal Graph Cut Approach","created":"2025-05-26","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":"2310.16290","title":"Fair Adaptive Experiments","created":"2023-10-25","cited_by_count":4},{"id":"2407.01186","title":"Data fusion for efficiency gain in ATE estimation: A practical review with simulations","created":"2024-07-01","cited_by_count":4},{"id":"2304.00420","title":"Experimentation Platforms Meet Reinforcement Learning: Bayesian Sequential Decision-Making for Continuous Monitoring","created":"2023-04-02","cited_by_count":3},{"id":"2312.06883","title":"Adaptive Experiments Toward Learning Treatment Effect Heterogeneity","created":"2023-12-11","cited_by_count":3},{"id":"2406.14380","title":"Estimating Treatment Effects under Algorithmic Interference: A Structured Neural Networks Approach","created":"2024-06-20","cited_by_count":3},{"id":"2008.07957","title":"Idle vehicle repositioning for dynamic ride-sharing","created":"2020-08-18","cited_by_count":2},{"id":"2111.03908","title":"An Online Sequential Test for Qualitative Treatment Effects","created":"2021-11-06","cited_by_count":2},{"id":"2407.17910","title":"Causal Deepsets for Off-policy Evaluation under Spatial or Spatio-temporal Interferences","created":"2024-07-25","cited_by_count":2},{"id":"2506.10677","title":"Exploiting Similarities in A/B Testing with Off-Policy Estimation","created":"2025-06-12","cited_by_count":2},{"id":"2506.12654","title":"Robust and efficient multiple-unit switchback experimentation","created":"2025-06-14","cited_by_count":2},{"id":"2507.18118","title":"A Two-armed Bandit Framework for A/B Testing","created":"2025-07-24","cited_by_count":2},{"id":"1911.02192","title":"Optimal Design of Experiments on Riemannian Manifolds","created":"2019-11-06","cited_by_count":1},{"id":"2410.08441","title":"A scientific review on advances in statistical methods for crossover design","created":"2024-10-11","cited_by_count":1},{"id":"2411.01405","title":"Computing Experiment-Constrained D-Optimal Designs","created":"2024-11-03","cited_by_count":1},{"id":"2411.19789","title":"Adjusting auxiliary variables under approximate neighborhood interference","created":"2024-11-29","cited_by_count":1},{"id":"2501.14602","title":"Minimax Optimal Design with Spillover and Carryover Effects","created":"2025-01-24","cited_by_count":1},{"id":"2505.22492","title":"Demystifying the Paradox of Importance Sampling with an Estimated History-Dependent Behavior Policy in Off-Policy Evaluation","created":"2025-05-28","cited_by_count":1},{"id":"2506.03062","title":"Multi-Metric Adaptive Experimental Design Under a Fixed Budget with Validation","created":"2025-06-03","cited_by_count":1},{"id":"2506.22536","title":"Strategic A/B testing via Maximum Probability-driven Two-armed Bandit","created":"2025-06-27","cited_by_count":1}],"next_cursor":null}