{"list":"other","total":73,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"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":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"id":"1705.10528","title":"Constrained Policy Optimization","created":"2017-05-30","cited_by_count":983},{"id":"1703.10593","title":"Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks","created":"2017-03-30","cited_by_count":707},{"id":"1708.05866","title":"A Brief Survey of Deep Reinforcement Learning","created":"2017-08-19","cited_by_count":483},{"id":"1809.07426","title":"Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding","created":"2018-09-19","cited_by_count":476},{"id":"1704.06888","title":"Time-Contrastive Networks: Self-Supervised Learning from Video","created":"2017-04-23","cited_by_count":459},{"id":"2009.13303","title":"Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey","created":"2020-09-24","cited_by_count":413},{"id":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"id":"1611.05763","title":"Learning to reinforcement learn","created":"2016-11-17","cited_by_count":377},{"id":"1604.06057","title":"Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation","created":"2016-04-20","cited_by_count":286},{"id":"1602.05352","title":"Recommendations as Treatments: Debiasing Learning and Evaluation","created":"2016-02-17","cited_by_count":248},{"id":"1802.10269","title":"Selective Experience Replay for Lifelong Learning","created":"2018-02-28","cited_by_count":241},{"id":"2010.03240","title":"Bias and Debias in Recommender System: A Survey and Future Directions","created":"2020-10-07","cited_by_count":240},{"id":"1905.10615","title":"Adversarial Policies: Attacking Deep Reinforcement Learning","created":"2019-05-25","cited_by_count":214},{"id":"1804.11192","title":"Explainable Recommendation: A Survey and New Perspectives","created":"2018-04-30","cited_by_count":210},{"id":"1809.02925","title":"Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning","created":"2018-09-09","cited_by_count":204},{"id":"2101.06286","title":"Reinforcement learning based recommender systems: A survey","created":"2021-01-15","cited_by_count":188},{"id":"1812.02353","title":"Top-K Off-Policy Correction for a REINFORCE Recommender System","created":"2018-12-06","cited_by_count":182},{"id":"1905.10958","title":"Explainable Reinforcement Learning Through a Causal Lens","created":"2019-05-27","cited_by_count":177},{"id":"1703.06748","title":"Tactics of Adversarial Attack on Deep Reinforcement Learning Agents","created":"2017-03-08","cited_by_count":166},{"id":"1810.09202","title":"Graph Convolutional Reinforcement Learning","created":"2018-10-22","cited_by_count":152},{"id":"1906.04477","title":"Causal Discovery with Reinforcement Learning","created":"2019-06-11","cited_by_count":145},{"id":"1803.09956","title":"Learning Synergies between Pushing and Grasping with Self-supervised Deep Reinforcement Learning","created":"2018-03-27","cited_by_count":128},{"id":"1904.12575","title":"Knowledge Graph Convolutional Networks for Recommender Systems","created":"2019-03-18","cited_by_count":121},{"id":"1906.05237","title":"Reinforcement Knowledge Graph Reasoning for Explainable Recommendation","created":"2019-06-12","cited_by_count":102},{"id":"1807.01473","title":"Supervised Reinforcement Learning with Recurrent Neural Network for Dynamic Treatment Recommendation","created":"2018-07-04","cited_by_count":101},{"id":"1805.02343","title":"Deep Reinforcement Learning for Page-wise Recommendations","created":"2018-05-07","cited_by_count":100},{"id":"1909.04847","title":"RecSim: A Configurable Simulation Platform for Recommender Systems","created":"2019-09-11","cited_by_count":94},{"id":"1711.08946","title":"Action Branching Architectures for Deep Reinforcement Learning","created":"2017-11-24","cited_by_count":92},{"id":"2006.09001","title":"RL-CycleGAN: Reinforcement Learning Aware Simulation-To-Real","created":"2020-06-16","cited_by_count":91},{"id":"1902.05570","title":"Reinforcement Learning to Optimize Long-term User Engagement in Recommender Systems","created":"2019-02-13","cited_by_count":90},{"id":"1805.10000","title":"Virtual-Taobao: Virtualizing Real-world Online Retail Environment for Reinforcement Learning","created":"2018-05-25","cited_by_count":80},{"id":"1709.10489","title":"Self-supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigation","created":"2017-09-29","cited_by_count":77},{"id":"1802.06501","title":"Recommendations with Negative Feedback via Pairwise Deep Reinforcement Learning","created":"2018-02-19","cited_by_count":71},{"id":"1808.00720","title":"RecoGym: A Reinforcement Learning Environment for the problem of Product Recommendation in Online Advertising","created":"2018-08-02","cited_by_count":65},{"id":"1812.10613","title":"Generative Adversarial User Model for Reinforcement Learning Based Recommendation System","created":"2018-12-27","cited_by_count":64},{"id":"1901.08162","title":"Causal Reasoning from Meta-reinforcement Learning","created":"2019-01-23","cited_by_count":53},{"id":"2006.05779","title":"Self-Supervised Reinforcement Learning for Recommender Systems","created":"2020-06-10","cited_by_count":49},{"id":"1910.12908","title":"Certified Adversarial Robustness for Deep Reinforcement Learning","created":"2019-10-28","cited_by_count":47},{"id":"1909.03602","title":"DEAR: Deep Reinforcement Learning for Online Advertising Impression in Recommender Systems","created":"2019-09-09","cited_by_count":44},{"id":"2003.05753","title":"Reinforced Negative Sampling over Knowledge Graph for Recommendation","created":"2020-03-12","cited_by_count":40},{"id":"2006.10389","title":"Interactive Recommender System via Knowledge Graph-enhanced Reinforcement Learning","created":"2020-06-18","cited_by_count":40},{"id":"2106.14421","title":"Causal Reinforcement Learning using Observational and Interventional Data","created":"2021-06-28","cited_by_count":39},{"id":"1809.09337","title":"A Survey of Learning Causality with Data: Problems and Methods","created":"2018-09-25","cited_by_count":37},{"id":"1801.00209","title":"Deep Reinforcement Learning for List-wise Recommendations","created":"2017-12-30","cited_by_count":35},{"id":"1803.00710","title":"Reinforcement Learning to Rank in E-Commerce Search Engine: Formalization, Analysis, and Application","created":"2018-03-02","cited_by_count":34},{"id":"1911.03845","title":"Model-Based Reinforcement Learning with Adversarial Training for Online Recommendation","created":"2019-11-10","cited_by_count":33},{"id":"1810.12027","title":"Deep Reinforcement Learning based Recommendation with Explicit User-Item Interactions Modeling","created":"2018-10-29","cited_by_count":31},{"id":"1811.05869","title":"Large-scale Interactive Recommendation with Tree-structured Policy Gradient","created":"2018-11-14","cited_by_count":30},{"id":"2003.00097","title":"Jointly Learning to Recommend and Advertise","created":"2020-02-28","cited_by_count":27},{"id":"1809.06260","title":"Learning to Collaborate: Multi-Scenario Ranking via Multi-Agent Reinforcement Learning","created":"2018-09-17","cited_by_count":23},{"id":"1802.04162","title":"Policy Gradients for Contextual Recommendations","created":"2018-02-12","cited_by_count":21},{"id":"2102.07359","title":"Intelligent Electric Vehicle Charging Recommendation Based on Multi-Agent Reinforcement Learning","created":"2021-02-15","cited_by_count":20},{"id":"2004.08068","title":"Knowledge-guided Deep Reinforcement Learning for Interactive Recommendation","created":"2020-04-17","cited_by_count":18},{"id":"1907.06584","title":"Environment Reconstruction with Hidden Confounders for Reinforcement Learning based Recommendation","created":"2019-07-12","cited_by_count":16},{"id":"1905.07089","title":"Exact-K Recommendation via Maximal Clique Optimization","created":"2019-05-17","cited_by_count":14},{"id":"2010.07035","title":"MARS-Gym: A Gym framework to model, train, and evaluate Recommender Systems for Marketplaces","created":"2020-09-30","cited_by_count":13},{"id":"2011.02248","title":"Generative Inverse Deep Reinforcement Learning for Online Recommendation","created":"2020-11-04","cited_by_count":12},{"id":"2006.07934","title":"Adversarial Attacks and Detection on Reinforcement Learning-Based Interactive Recommender Systems","created":"2020-06-14","cited_by_count":9},{"id":"2008.09369","title":"Learning to Collaborate in Multi-Module Recommendation via Multi-Agent Reinforcement Learning without Communication","created":"2020-08-21","cited_by_count":8},{"id":"1906.11462","title":"Toward Simulating Environments in Reinforcement Learning Based Recommendations","created":"2019-06-27","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":"2104.02981","title":"Reinforcement Learning with a Disentangled Universal Value Function for Item Recommendation","created":"2021-04-07","cited_by_count":4}],"next_cursor":null}