{"list":"other","total":68,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"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":"1912.04977","title":"Advances and Open Problems in Federated Learning","created":"2019-12-10","cited_by_count":3046},{"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":"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":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"1908.07873","title":"Federated Learning: Challenges, Methods, and Future Directions","created":"2019-08-21","cited_by_count":1538},{"id":"1907.02189","title":"On the Convergence of FedAvg on Non-IID Data","created":"2019-07-04","cited_by_count":1229},{"id":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"id":"1906.08935","title":"Deep Leakage from Gradients","created":"2019-06-21","cited_by_count":1021},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"1902.01046","title":"Towards Federated Learning at Scale: System Design","created":"2019-02-04","cited_by_count":832},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"1705.08926","title":"Counterfactual Multi-Agent Policy Gradients","created":"2017-05-24","cited_by_count":751},{"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":"1911.10635","title":"Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms","created":"2019-11-24","cited_by_count":567},{"id":"1706.05296","title":"Value-Decomposition Networks For Cooperative Multi-Agent Learning","created":"2017-06-16","cited_by_count":503},{"id":"1507.06527","title":"Deep Recurrent Q-Learning for Partially Observable MDPs","created":"2015-07-23","cited_by_count":465},{"id":"1804.05271","title":"Adaptive Federated Learning in Resource Constrained Edge Computing Systems","created":"2018-04-14","cited_by_count":409},{"id":"1909.11875","title":"Federated Learning in Mobile Edge Networks: A Comprehensive Survey","created":"2019-09-26","cited_by_count":408},{"id":"1605.07736","title":"Learning Multiagent Communication with Backpropagation","created":"2016-05-25","cited_by_count":366},{"id":"1804.08333","title":"Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge","created":"2018-04-23","cited_by_count":352},{"id":"1701.07274","title":"Deep Reinforcement Learning: An Overview","created":"2017-01-25","cited_by_count":333},{"id":"1610.03295","title":"Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving","created":"2016-10-11","cited_by_count":311},{"id":"1803.00933","title":"Distributed Prioritized Experience Replay","created":"2018-03-02","cited_by_count":269},{"id":"2104.07914","title":"Federated Learning for Internet of Things: A Comprehensive Survey","created":"2021-04-16","cited_by_count":252},{"id":"1301.3836","title":"The Complexity of Decentralized Control of Markov Decision Processes","created":"2013-01-16","cited_by_count":231},{"id":"1704.02532","title":"Deep Reinforcement Learning framework for Autonomous Driving","created":"2017-04-08","cited_by_count":225},{"id":"1702.03037","title":"Multi-agent Reinforcement Learning in Sequential Social Dilemmas","created":"2017-02-10","cited_by_count":209},{"id":"1812.02903","title":"Applied Federated Learning: Improving Google Keyboard Query Suggestions","created":"2018-12-07","cited_by_count":204},{"id":"1804.08617","title":"Distributed Distributional Deterministic Policy Gradients","created":"2018-04-23","cited_by_count":199},{"id":"1802.08757","title":"Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents","created":"2018-02-23","cited_by_count":194},{"id":"1511.08779","title":"Multiagent Cooperation and Competition with Deep Reinforcement Learning","created":"2015-11-27","cited_by_count":184},{"id":"2003.02133","title":"Threats to Federated Learning: A Survey","created":"2020-03-04","cited_by_count":178},{"id":"1808.04866","title":"Mitigating Sybils in Federated Learning Poisoning","created":"2018-08-14","cited_by_count":161},{"id":"1703.06182","title":"Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability","created":"2017-03-17","cited_by_count":148},{"id":"1908.03963","title":"A Review of Cooperative Multi-Agent Deep Reinforcement Learning","created":"2019-08-11","cited_by_count":147},{"id":"1702.05800","title":"Revisiting Distributed Synchronous SGD","created":"2017-02-19","cited_by_count":142},{"id":"2009.13012","title":"Federated Learning for Internet of Things: Recent Advances, Taxonomy, and Open Challenges","created":"2020-09-28","cited_by_count":139},{"id":"1702.08887","title":"Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning","created":"2017-02-28","cited_by_count":117},{"id":"1507.04296","title":"Massively Parallel Methods for Deep Reinforcement Learning","created":"2015-07-15","cited_by_count":82},{"id":"1611.02247","title":"Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic","created":"2016-11-07","cited_by_count":81},{"id":"2001.07845","title":"Convergence Time Optimization for Federated Learning over Wireless Networks","created":"2020-01-22","cited_by_count":81},{"id":"1809.07857","title":"In-Edge AI: Intelligentizing Mobile Edge Computing, Caching and Communication by Federated Learning","created":"2018-09-19","cited_by_count":80},{"id":"1909.08525","title":"Measure Contribution of Participants in Federated Learning","created":"2019-09-17","cited_by_count":79},{"id":"1512.04455","title":"Memory-based control with recurrent neural networks","created":"2015-12-14","cited_by_count":78},{"id":"1901.06455","title":"Lifelong Federated Reinforcement Learning: A Learning Architecture for Navigation in Cloud Robotic Systems","created":"2019-01-19","cited_by_count":78},{"id":"1703.06692","title":"QMDP-Net: Deep Learning for Planning under Partial Observability","created":"2017-03-20","cited_by_count":51},{"id":"1804.06309","title":"On Improving Deep Reinforcement Learning for POMDPs","created":"2018-04-17","cited_by_count":50},{"id":"1910.06001","title":"Federated Transfer Reinforcement Learning for Autonomous Driving","created":"2019-10-14","cited_by_count":44},{"id":"1812.07478","title":"Multi-objective Evolutionary Federated Learning","created":"2018-12-18","cited_by_count":42},{"id":"1801.05757","title":"Experience-driven Networking: A Deep Reinforcement Learning based Approach","created":"2018-01-17","cited_by_count":41},{"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":"1705.04862","title":"Efficient Parallel Methods for Deep Reinforcement Learning","created":"2017-05-13","cited_by_count":32},{"id":"1811.07029","title":"Modelling the Dynamic Joint Policy of Teammates with Attention Multi-agent DDPG","created":"2018-11-13","cited_by_count":20},{"id":"1810.04118","title":"Semi-supervised Deep Reinforcement Learning in Support of IoT and Smart City Services","created":"2018-10-09","cited_by_count":15},{"id":"2002.05485","title":"Deep Reinforcement Learning Based Mode Selection and Resource Allocation for Cellular V2X Communications","created":"2020-02-13","cited_by_count":14},{"id":"2002.02581","title":"Dynamic Energy Dispatch Based on Deep Reinforcement Learning in IoT-Driven Smart Isolated Microgrids","created":"2020-02-07","cited_by_count":13},{"id":"2004.01098","title":"Information State Embedding in Partially Observable Cooperative Multi-Agent Reinforcement Learning","created":"2020-04-02","cited_by_count":13},{"id":"2103.06473","title":"Multi-Task Federated Reinforcement Learning with Adversaries","created":"2021-03-11","cited_by_count":13},{"id":"1906.07860","title":"Multi-user Resource Control with Deep Reinforcement Learning in IoT Edge Computing","created":"2019-06-19","cited_by_count":5},{"id":"1904.08100","title":"Patent Analytics Based on Feature Vector Space Model: A Case of IoT","created":"2019-04-17","cited_by_count":3},{"id":"2102.07019","title":"Enhancing WiFi Multiple Access Performance with Federated Deep Reinforcement Learning","created":"2021-02-13","cited_by_count":2}],"next_cursor":null}