{"list":"other","total":53,"rows":[{"id":"1707.08114","title":"A Survey on Multi-Task Learning","created":"2017-07-25","cited_by_count":840},{"id":"1703.06856","title":"Counterfactual Fairness","created":"2017-03-20","cited_by_count":804},{"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":"1505.06279","title":"The Benefit of Multitask Representation Learning","created":"2015-05-23","cited_by_count":195},{"id":"1802.07281","title":"Fairness of Exposure in Rankings","created":"2018-02-20","cited_by_count":190},{"id":"1605.07139","title":"Fairness in Learning: Classic and Contextual Bandits","created":"2016-05-23","cited_by_count":168},{"id":"1305.2545","title":"Bandits with Knapsacks","created":"2013-05-11","cited_by_count":164},{"id":"1503.02834","title":"Doubly Robust Policy Evaluation and Optimization","created":"2015-03-10","cited_by_count":158},{"id":"1506.03271","title":"Explore no more: Improved high-probability regret bounds for non-stochastic bandits","created":"2015-06-10","cited_by_count":120},{"id":"1803.09353","title":"Stochastic bandits robust to adversarial corruptions","created":"2018-03-25","cited_by_count":119},{"id":"1612.01205","title":"Optimal and Adaptive Off-policy Evaluation in Contextual Bandits","created":"2016-12-04","cited_by_count":111},{"id":"1401.8257","title":"Online Clustering of Bandits","created":"2014-01-31","cited_by_count":102},{"id":"1606.03203","title":"Causal Bandits: Learning Good Interventions via Causal Inference","created":"2016-06-10","cited_by_count":101},{"id":"2102.05406","title":"Non-stationary Reinforcement Learning without Prior Knowledge: An Optimal Black-box Approach","created":"2021-02-10","cited_by_count":98},{"id":"1902.08647","title":"Better Algorithms for Stochastic Bandits with Adversarial Corruptions","created":"2019-02-22","cited_by_count":92},{"id":"1402.5758","title":"Bandits with concave rewards and convex knapsacks","created":"2014-02-24","cited_by_count":83},{"id":"1507.06738","title":"Linear Contextual Bandits with Knapsacks","created":"2015-07-24","cited_by_count":82},{"id":"1306.3171","title":"Confidence Intervals and Hypothesis Testing for High-Dimensional Regression","created":"2013-06-13","cited_by_count":79},{"id":"1907.10516","title":"Achieving Fairness in the Stochastic Multi-armed Bandit Problem","created":"2019-07-23","cited_by_count":78},{"id":"1811.11881","title":"Adversarial Bandits with Knapsacks","created":"2018-11-28","cited_by_count":73},{"id":"1902.00980","title":"A New Algorithm for Non-stationary Contextual Bandits: Efficient, Optimal, and Parameter-free","created":"2019-02-03","cited_by_count":71},{"id":"1909.03539","title":"Personalized HeartSteps: A Reinforcement Learning Algorithm for Optimizing Physical Activity","created":"2019-09-08","cited_by_count":70},{"id":"1802.06936","title":"Online Learning with an Unknown Fairness Metric","created":"2018-02-20","cited_by_count":62},{"id":"2011.04020","title":"High-Dimensional Sparse Linear Bandits","created":"2020-11-08","cited_by_count":61},{"id":"1602.04282","title":"Conservative Bandits","created":"2016-02-13","cited_by_count":59},{"id":"1611.06426","title":"Conservative Contextual Linear Bandits","created":"2016-11-19","cited_by_count":57},{"id":"1802.03692","title":"Nearly Optimal Adaptive Procedure with Change Detection for Piecewise-Stationary Bandit","created":"2018-02-11","cited_by_count":50},{"id":"1306.0811","title":"A Gang of Bandits","created":"2013-06-04","cited_by_count":49},{"id":"2006.02948","title":"Low-Rank Generalized Linear Bandit Problems","created":"2020-06-04","cited_by_count":49},{"id":"1705.08618","title":"Multi-Task Learning for Contextual Bandits","created":"2017-05-24","cited_by_count":47},{"id":"1707.01875","title":"Calibrated Fairness in Bandits","created":"2017-07-06","cited_by_count":43},{"id":"2103.02735","title":"Fairness of Exposure in Stochastic Bandits","created":"2021-03-03","cited_by_count":43},{"id":"1701.02789","title":"Identifying Best Interventions through Online Importance Sampling","created":"2017-01-10","cited_by_count":39},{"id":"1605.04070","title":"A Reinforcement Learning System to Encourage Physical Activity in Diabetes Patients","created":"2016-05-13","cited_by_count":38},{"id":"2012.07058","title":"Budgeted and Non-budgeted Causal Bandits","created":"2020-12-13","cited_by_count":38},{"id":"2106.02988","title":"Causal Bandits with Unknown Graph Structure","created":"2021-06-05","cited_by_count":37},{"id":"2004.06230","title":"Power Constrained Bandits","created":"2020-04-13","cited_by_count":30},{"id":"1504.06937","title":"Algorithms with Logarithmic or Sublinear Regret for Constrained Contextual Bandits","created":"2015-04-27","cited_by_count":29},{"id":"2003.01803","title":"MOTS: Minimax Optimal Thompson Sampling","created":"2020-03-03","cited_by_count":28},{"id":"1505.00146","title":"Thompson Sampling for Budgeted Multi-armed Bandits","created":"2015-05-01","cited_by_count":24},{"id":"2008.01571","title":"IntelligentPooling: Practical Thompson Sampling for mHealth","created":"2020-07-31","cited_by_count":24},{"id":"2010.10182","title":"The Elliptical Potential Lemma Revisited","created":"2020-10-20","cited_by_count":23},{"id":"2102.01229","title":"Doubly robust Thompson sampling for linear payoffs","created":"2021-02-01","cited_by_count":21},{"id":"2002.03218","title":"Conservative Exploration in Reinforcement Learning","created":"2020-02-08","cited_by_count":20},{"id":"2002.03221","title":"Improved Algorithms for Conservative Exploration in Bandits","created":"2020-02-08","cited_by_count":16},{"id":"1711.05928","title":"Budget-Constrained Multi-Armed Bandits with Multiple Plays","created":"2017-11-16","cited_by_count":13},{"id":"2008.09472","title":"Offline Contextual Multi-armed Bandits for Mobile Health Interventions: A Case Study on Emotion Regulation","created":"2020-08-21","cited_by_count":13},{"id":"2010.12102","title":"Achieving User-Side Fairness in Contextual Bandits","created":"2020-10-22","cited_by_count":11},{"id":"2101.07781","title":"Minimax Off-Policy Evaluation for Multi-Armed Bandits","created":"2021-01-19","cited_by_count":9},{"id":"1507.07880","title":"Optimally Confident UCB: Improved Regret for Finite-Armed Bandits","created":"2015-07-28","cited_by_count":7},{"id":"1405.3536","title":"Improving offline evaluation of contextual bandit algorithms via bootstrapping techniques","created":"2014-05-14","cited_by_count":3},{"id":"1911.04389","title":"A Biologically Plausible Benchmark for Contextual Bandit Algorithms in Precision Oncology Using in vitro Data","created":"2019-11-11","cited_by_count":2}],"next_cursor":null}