{"list":"other","total":68,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1606.03476","title":"Generative Adversarial Imitation Learning","created":"2016-06-10","cited_by_count":1597},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"id":"1603.09320","title":"Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs","created":"2016-03-30","cited_by_count":861},{"id":"1511.06581","title":"Dueling Network Architectures for Deep Reinforcement Learning","created":"2015-11-20","cited_by_count":785},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"1709.00103","title":"Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning","created":"2017-08-31","cited_by_count":687},{"id":"1507.06527","title":"Deep Recurrent Q-Learning for Partially Observable MDPs","created":"2015-07-23","cited_by_count":465},{"id":"1806.02473","title":"Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation","created":"2018-06-07","cited_by_count":364},{"id":"1908.08796","title":"Reinforcement Learning in Healthcare: A Survey","created":"2019-08-22","cited_by_count":310},{"id":"1604.06057","title":"Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation","created":"2016-04-20","cited_by_count":286},{"id":"1706.10295","title":"Noisy Networks for Exploration","created":"2017-06-30","cited_by_count":266},{"id":"1712.01208","title":"The Case for Learned Index Structures","created":"2017-12-04","cited_by_count":188},{"id":"1810.07862","title":"Applications of Deep Reinforcement Learning in Communications and Networking: A Survey","created":"2018-10-18","cited_by_count":167},{"id":"1707.02286","title":"Emergence of Locomotion Behaviours in Rich Environments","created":"2017-07-07","cited_by_count":165},{"id":"1706.01905","title":"Parameter Space Noise for Exploration","created":"2017-06-06","cited_by_count":161},{"id":"1601.01280","title":"Language to Logical Form with Neural Attention","created":"2016-01-06","cited_by_count":158},{"id":"2005.06247","title":"Explainable Reinforcement Learning: A Survey","created":"2020-05-13","cited_by_count":141},{"id":"1711.04436","title":"SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning","created":"2017-11-13","cited_by_count":135},{"id":"1810.01963","title":"Learning Scheduling Algorithms for Data Processing Clusters","created":"2018-10-03","cited_by_count":134},{"id":"1810.12282","title":"Assessing Generalization in Deep Reinforcement Learning","created":"2018-10-29","cited_by_count":133},{"id":"1807.01473","title":"Supervised Reinforcement Learning with Recurrent Neural Network for Dynamic Treatment Recommendation","created":"2018-07-04","cited_by_count":101},{"id":"2101.12631","title":"A Comprehensive Survey and Experimental Comparison of Graph-Based Approximate Nearest Neighbor Search","created":"2021-01-29","cited_by_count":82},{"id":"1609.08667","title":"Deep Reinforcement Learning for Mention-Ranking Coreference Models","created":"2016-09-27","cited_by_count":63},{"id":"2004.03814","title":"Bao: Learning to Steer Query Optimizers","created":"2020-04-08","cited_by_count":62},{"id":"1505.06807","title":"MLlib: Machine Learning in Apache Spark","created":"2015-05-26","cited_by_count":55},{"id":"2009.06847","title":"Toward Deep Supervised Anomaly Detection: Reinforcement Learning from Partially Labeled Anomaly Data","created":"2020-09-15","cited_by_count":42},{"id":"1803.00259","title":"Deep Reinforcement Learning for Sponsored Search Real-time Bidding","created":"2018-03-01","cited_by_count":34},{"id":"1804.06087","title":"Rafiki: Machine Learning as an Analytics Service System","created":"2018-04-17","cited_by_count":33},{"id":"1808.03196","title":"Learning to Optimize Join Queries With Deep Reinforcement Learning","created":"2018-08-09","cited_by_count":32},{"id":"1807.02264","title":"Variance Reduction for Reinforcement Learning in Input-Driven Environments","created":"2018-07-06","cited_by_count":30},{"id":"1906.08986","title":"Database Meets Deep Learning: Challenges and Opportunities","created":"2019-06-21","cited_by_count":30},{"id":"1902.00330","title":"Joint Entity Linking with Deep Reinforcement Learning","created":"2019-02-01","cited_by_count":27},{"id":"1803.00055","title":"Deep Reinforcement Learning for Join Order Enumeration","created":"2018-02-28","cited_by_count":25},{"id":"1809.06260","title":"Learning to Collaborate: Multi-Scenario Ranking via Multi-Agent Reinforcement Learning","created":"2018-09-17","cited_by_count":23},{"id":"1911.00061","title":"DeepLine: AutoML Tool for Pipelines Generation using Deep Reinforcement Learning and Hierarchical Actions Filtering","created":"2019-10-31","cited_by_count":21},{"id":"2004.10398","title":"Sequential Anomaly Detection using Inverse Reinforcement Learning","created":"2020-04-22","cited_by_count":20},{"id":"2004.10898","title":"Qd-tree: Learning Data Layouts for Big Data Analytics","created":"2020-04-22","cited_by_count":18},{"id":"1901.05152","title":"SkinnerDB: Regret-Bounded Query Evaluation via Reinforcement Learning","created":"2019-01-16","cited_by_count":17},{"id":"2006.06069","title":"Robust Spammer Detection by Nash Reinforcement Learning","created":"2020-06-10","cited_by_count":17},{"id":"1603.07954","title":"Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning","created":"2016-03-25","cited_by_count":16},{"id":"1907.06584","title":"Environment Reconstruction with Hidden Confounders for Reinforcement Learning based Recommendation","created":"2019-07-12","cited_by_count":16},{"id":"2010.10246","title":"MLCask: Efficient Management of Component Evolution in Collaborative Data Analytics Pipelines","created":"2020-10-17","cited_by_count":15},{"id":"1902.10319","title":"Neural Packet Classification","created":"2019-02-27","cited_by_count":14},{"id":"2007.01135","title":"Student-Teacher Curriculum Learning via Reinforcement Learning: Predicting Hospital Inpatient Admission Location","created":"2020-07-01","cited_by_count":10},{"id":"2002.10990","title":"G-Learner and GIRL: Goal Based Wealth Management with Reinforcement Learning","created":"2020-02-25","cited_by_count":9},{"id":"2002.11780","title":"Black or White? How to Develop an AutoTuner for Memory-based Analytics [Extended Version]","created":"2020-02-26","cited_by_count":9},{"id":"1801.05643","title":"The Case for Automatic Database Administration using Deep Reinforcement Learning","created":"2018-01-17","cited_by_count":8},{"id":"1801.06077","title":"The QLBS Q-Learner Goes NuQLear: Fitted Q Iteration, Inverse RL, and Option Portfolios","created":"2018-01-17","cited_by_count":8},{"id":"1911.11689","title":"Join Query Optimization with Deep Reinforcement Learning Algorithms","created":"2019-11-26","cited_by_count":7},{"id":"1903.01363","title":"Opportunistic View Materialization with Deep Reinforcement Learning","created":"2019-03-04","cited_by_count":6},{"id":"1902.08882","title":"Aggregating E-commerce Search Results from Heterogeneous Sources via Hierarchical Reinforcement Learning","created":"2019-02-24","cited_by_count":5},{"id":"1803.01016","title":"Model-Free Control for Distributed Stream Data Processing using Deep Reinforcement Learning","created":"2018-03-02","cited_by_count":4},{"id":"1909.02119","title":"Inductive-bias-driven Reinforcement Learning For Efficient Schedules in Heterogeneous Clusters","created":"2019-09-04","cited_by_count":4},{"id":"2105.10329","title":"Polyjuice: High-Performance Transactions via Learned Concurrency Control","created":"2021-05-21","cited_by_count":4},{"id":"2007.10568","title":"Buffer Pool Aware Query Scheduling via Deep Reinforcement Learning","created":"2020-07-21","cited_by_count":3},{"id":"1909.07440","title":"Learning Index Selection with Structured Action Spaces","created":"2019-09-16","cited_by_count":2},{"id":"1911.12122","title":"Towards Similarity Graphs Constructed by Deep Reinforcement Learning","created":"2019-11-27","cited_by_count":2},{"id":"2011.07160","title":"Phoebe: Reuse-Aware Online Caching with Reinforcement Learning for Emerging Storage Models","created":"2020-11-13","cited_by_count":2},{"id":"1912.07001","title":"Progressive Neural Index Search for Database System","created":"2019-12-15","cited_by_count":1},{"id":"2006.16529","title":"Lachesis: Automatic Partitioning for UDF-Centric Analytics","created":"2020-06-30","cited_by_count":1}],"next_cursor":null}