{"list":"other","total":52,"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":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"1909.05207","title":"Introduction to Online Convex Optimization","created":"2019-09-07","cited_by_count":803},{"id":"2002.00444","title":"Deep Reinforcement Learning for Autonomous Driving: A Survey","created":"2020-02-02","cited_by_count":721},{"id":"1803.11485","title":"QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","created":"2018-03-30","cited_by_count":708},{"id":"1605.06676","title":"Learning to Communicate with Deep Multi-Agent Reinforcement Learning","created":"2016-05-21","cited_by_count":575},{"id":"1708.05866","title":"A Brief Survey of Deep Reinforcement Learning","created":"2017-08-19","cited_by_count":483},{"id":"1905.05408","title":"QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning","created":"2019-05-14","cited_by_count":379},{"id":"1604.06778","title":"Benchmarking Deep Reinforcement Learning for Continuous Control","created":"2016-04-22","cited_by_count":371},{"id":"1701.07274","title":"Deep Reinforcement Learning: An Overview","created":"2017-01-25","cited_by_count":333},{"id":"1908.08796","title":"Reinforcement Learning in Healthcare: A Survey","created":"2019-08-22","cited_by_count":310},{"id":"1810.05587","title":"A Survey and Critique of Multiagent Deep Reinforcement Learning","created":"2018-10-12","cited_by_count":177},{"id":"1810.07862","title":"Applications of Deep Reinforcement Learning in Communications and Networking: A Survey","created":"2018-10-18","cited_by_count":167},{"id":"1906.03926","title":"A Survey of Reinforcement Learning Informed by Natural Language","created":"2019-06-10","cited_by_count":154},{"id":"1703.06182","title":"Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability","created":"2017-03-17","cited_by_count":148},{"id":"1812.11794","title":"Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applications","created":"2018-12-31","cited_by_count":127},{"id":"1906.05799","title":"Deep Reinforcement Learning for Cyber Security","created":"2019-06-13","cited_by_count":95},{"id":"1711.09602","title":"Deep Reinforcement Learning for Sepsis Treatment","created":"2017-11-27","cited_by_count":71},{"id":"1705.08422","title":"Continuous State-Space Models for Optimal Sepsis Treatment - a Deep Reinforcement Learning Approach","created":"2017-05-23","cited_by_count":68},{"id":"1611.03531","title":"Estimating Dynamic Treatment Regimes in Mobile Health Using V-learning","created":"2016-11-10","cited_by_count":65},{"id":"1911.06992","title":"Learning Efficient Multi-agent Communication: An Information Bottleneck Approach","created":"2019-11-16","cited_by_count":61},{"id":"2012.07450","title":"FedHome: Cloud-Edge based Personalized Federated Learning for In-Home Health Monitoring","created":"2020-12-14","cited_by_count":61},{"id":"2011.03615","title":"Single and Multi-Agent Deep Reinforcement Learning for AI-Enabled Wireless Networks: A Tutorial","created":"2020-11-06","cited_by_count":60},{"id":"1711.03985","title":"Applications of Deep Learning and Reinforcement Learning to Biological Data","created":"2017-11-10","cited_by_count":45},{"id":"1907.09059","title":"Deep Reinforcement Learning for Autonomous Internet of Things: Model, Applications and Challenges","created":"2019-07-22","cited_by_count":37},{"id":"2002.06684","title":"R-MADDPG for Partially Observable Environments and Limited Communication","created":"2020-02-16","cited_by_count":36},{"id":"1901.04670","title":"Improving Sepsis Treatment Strategies by Combining Deep and Kernel-Based Reinforcement Learning","created":"2019-01-15","cited_by_count":34},{"id":"1912.05304","title":"Learning Agent Communication under Limited Bandwidth by Message Pruning","created":"2019-12-03","cited_by_count":31},{"id":"1703.09035","title":"Deep Deterministic Policy Gradient for Urban Traffic Light Control","created":"2017-03-27","cited_by_count":30},{"id":"2009.10601","title":"When Deep Reinforcement Learning Meets Federated Learning: Intelligent Multi-Timescale Resource Management for Multi-access Edge Computing in 5G Ultra Dense Network","created":"2020-09-22","cited_by_count":30},{"id":"2102.07247","title":"Reinforcement Learning for IoT Security: A Comprehensive Survey","created":"2021-02-14","cited_by_count":23},{"id":"1912.00498","title":"Optimization for Reinforcement Learning: From Single Agent to Cooperative Agents","created":"2019-12-01","cited_by_count":20},{"id":"2005.09059","title":"Basal Glucose Control in Type 1 Diabetes using Deep Reinforcement Learning: An In Silico Validation","created":"2020-05-18","cited_by_count":18},{"id":"1805.00200","title":"Falsification of Cyber-Physical Systems Using Deep Reinforcement Learning","created":"2018-05-01","cited_by_count":17},{"id":"2004.02315","title":"Multi-agent Reinforcement Learning for Resource Allocation in IoT networks with Edge Computing","created":"2020-04-05","cited_by_count":13},{"id":"2004.07311","title":"Edge Computing For Smart Health: Context-aware Approaches, Opportunities, and Challenges","created":"2020-04-15","cited_by_count":10},{"id":"1801.05915","title":"Security in Mobile Edge Caching with Reinforcement Learning","created":"2018-01-18","cited_by_count":9},{"id":"1904.13032","title":"A Deep Q-Learning Method for Downlink Power Allocation in Multi-Cell Networks","created":"2019-04-30","cited_by_count":7},{"id":"2002.07593","title":"Active Learning-based Classification in Automated Connected Vehicles","created":"2020-02-18","cited_by_count":7},{"id":"2008.07614","title":"DeepSlicing: Deep Reinforcement Learning Assisted Resource Allocation for Network Slicing","created":"2020-08-17","cited_by_count":7},{"id":"1805.11548","title":"The Actor Search Tree Critic (ASTC) for Off-Policy POMDP Learning in Medical Decision Making","created":"2018-05-29","cited_by_count":6},{"id":"1808.00667","title":"Deep Learning for Radio Resource Allocation in Multi-Cell Networks","created":"2018-08-02","cited_by_count":6},{"id":"1812.02658","title":"UAV-Assisted Relaying and Edge Computing: Scheduling and Trajectory Optimization","created":"2018-12-06","cited_by_count":6},{"id":"1908.03242","title":"Deep Reinforcement Learning for Network Slicing with Heterogeneous Resource Requirements and Time Varying Traffic Dynamics","created":"2019-08-08","cited_by_count":6},{"id":"1710.02913","title":"Artificial Neural Networks-Based Machine Learning for Wireless Networks: A Tutorial","created":"2017-10-09","cited_by_count":5},{"id":"1802.10440","title":"Precision medicine as a control problem: Using simulation and deep reinforcement learning to discover adaptive, personalized multi-cytokine therapy for sepsis","created":"2018-02-08","cited_by_count":5},{"id":"1611.02314","title":"Robust Hybrid Learning for Estimating Personalized Dynamic Treatment Regimens","created":"2016-11-07","cited_by_count":3},{"id":"1803.03586","title":"Towards 5G Enabled Tactile Robotic Telesurgery","created":"2018-03-09","cited_by_count":3},{"id":"2006.10843","title":"SSHealth: Toward Secure, Blockchain-Enabled Healthcare Systems","created":"2020-06-18","cited_by_count":3}],"next_cursor":null}