{"list":"other","total":60,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"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":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"1812.08434","title":"Graph Neural Networks: A Review of Methods and Applications","created":"2018-12-20","cited_by_count":1576},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"id":"1511.06581","title":"Dueling Network Architectures for Deep Reinforcement Learning","created":"2015-11-20","cited_by_count":785},{"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":"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":"1701.07274","title":"Deep Reinforcement Learning: An Overview","created":"2017-01-25","cited_by_count":333},{"id":"1810.02912","title":"Actor-Attention-Critic for Multi-Agent Reinforcement Learning","created":"2018-10-05","cited_by_count":261},{"id":"1301.3836","title":"The Complexity of Decentralized Control of Markov Decision Processes","created":"2013-01-16","cited_by_count":231},{"id":"1802.05438","title":"Mean Field Multi-Agent Reinforcement Learning","created":"2018-02-15","cited_by_count":207},{"id":"1811.12560","title":"An Introduction to Deep Reinforcement Learning","created":"2018-11-30","cited_by_count":206},{"id":"2006.10800","title":"Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","created":"2020-06-18","cited_by_count":197},{"id":"1802.08757","title":"Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents","created":"2018-02-23","cited_by_count":194},{"id":"1810.07862","title":"Applications of Deep Reinforcement Learning in Communications and Networking: A Survey","created":"2018-10-18","cited_by_count":167},{"id":"1708.05144","title":"Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation","created":"2017-08-17","cited_by_count":121},{"id":"1803.04311","title":"Deep Learning in Mobile and Wireless Networking: A Survey","created":"2018-03-12","cited_by_count":118},{"id":"1707.09183","title":"A Survey of Learning in Multiagent Environments: Dealing with Non-Stationarity","created":"2017-07-28","cited_by_count":94},{"id":"1808.00490","title":"Multi-Agent Deep Reinforcement Learning for Dynamic Power Allocation in Wireless Networks","created":"2018-08-01","cited_by_count":70},{"id":"1712.04301","title":"Deep Learning for IoT Big Data and Streaming Analytics: A Survey","created":"2017-12-09","cited_by_count":59},{"id":"1810.10408","title":"Multi-Agent Reinforcement Learning Based Resource Allocation for UAV Networks","created":"2018-10-24","cited_by_count":56},{"id":"2002.06215","title":"Resource Management in Wireless Networks via Multi-Agent Deep Reinforcement Learning","created":"2020-02-14","cited_by_count":42},{"id":"1802.06958","title":"Deep Reinforcement Learning for Dynamic Multichannel Access in Wireless Networks","created":"2018-02-20","cited_by_count":37},{"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":"1904.11082","title":"How You Act Tells a Lot: Privacy-Leakage Attack on Deep Reinforcement Learning","created":"2019-04-24","cited_by_count":29},{"id":"2009.11277","title":"Multi-Agent Deep Reinforcement Learning Based Trajectory Planning for Multi-UAV Assisted Mobile Edge Computing","created":"2020-09-23","cited_by_count":24},{"id":"2007.14297","title":"Cooperative Internet of UAVs: Distributed Trajectory Design by Multi-agent Deep Reinforcement Learning","created":"2020-07-28","cited_by_count":18},{"id":"1312.7606","title":"Distributed Policy Evaluation Under Multiple Behavior Strategies","created":"2013-12-30","cited_by_count":17},{"id":"1709.07080","title":"A Deep-Reinforcement Learning Approach for Software-Defined Networking Routing Optimization","created":"2017-09-20","cited_by_count":14},{"id":"1811.05053","title":"Distributed Cooperative Spectrum Sharing in UAV Networks Using Multi-Agent Reinforcement Learning","created":"2018-11-13","cited_by_count":12},{"id":"1807.09350","title":"Multi-Tenant Cross-Slice Resource Orchestration: A Deep Reinforcement Learning Approach","created":"2018-07-17","cited_by_count":10},{"id":"1809.04374","title":"A Collaborative Multi-agent Reinforcement Learning Anti-jamming Algorithm in Wireless Networks","created":"2018-09-12","cited_by_count":10},{"id":"1809.02934","title":"Reinforcement Learning for Decentralized Trajectory Design in Cellular UAV Networks with Sense-and-Send Protocol","created":"2018-09-09","cited_by_count":8},{"id":"1906.00777","title":"Multi-Drone 3D Trajectory Planning and Scheduling in Drone Assisted Radio Access Networks","created":"2019-05-30","cited_by_count":6},{"id":"2003.03433","title":"Reward Design in Cooperative Multi-agent Reinforcement Learning for Packet Routing","created":"2020-03-05","cited_by_count":6},{"id":"1812.02783","title":"Finite-Sample Analysis For Decentralized Batch Multi-Agent Reinforcement Learning With Networked Agents","created":"2018-12-06","cited_by_count":5},{"id":"1912.09302","title":"Multi-Agent Deep Reinforcement Learning based Spectrum Allocation for D2D Underlay Communications","created":"2019-12-18","cited_by_count":5},{"id":"2004.12095","title":"Deep Reinforcement Learning for Multi-Agent Power Control in Heterogeneous Networks","created":"2020-04-25","cited_by_count":5},{"id":"2010.09094","title":"Multi-Agent Reinforcement Learning in NOMA-aided UAV Networks for Cellular Offloading","created":"2020-10-18","cited_by_count":5},{"id":"2101.03273","title":"Robust and Scalable Routing with Multi-Agent Deep Reinforcement Learning for MANETs","created":"2021-01-09","cited_by_count":5},{"id":"1908.04685","title":"Learn to Compress CSI and Allocate Resources in Vehicular Networks","created":"2019-08-12","cited_by_count":4},{"id":"2002.08040","title":"Cellular UAV-to-Device Communications: Trajectory Design and Mode Selection by Multi-agent Deep Reinforcement Learning","created":"2020-02-19","cited_by_count":4},{"id":"1905.05256","title":"Deep Multi-Agent Reinforcement Learning Based Cooperative Edge Caching in Wireless Networks","created":"2019-05-13","cited_by_count":3},{"id":"1403.5723","title":"Game-theoretic Resource Allocation Methods for Device-to-Device (D2D) Communication","created":"2014-03-23","cited_by_count":2},{"id":"1706.09024","title":"Cache-enabled Wireless Networks with Opportunistic Interference Alignment","created":"2017-06-27","cited_by_count":2},{"id":"1710.00590","title":"Latency and Reliability-Aware Task Offloading and Resource Allocation for Mobile Edge Computing","created":"2017-10-02","cited_by_count":2},{"id":"1807.03537","title":"Soft-TTL: Time-Varying Fractional Caching","created":"2018-07-10","cited_by_count":2},{"id":"2010.05290","title":"Distributed Resource Allocation with Multi-Agent Deep Reinforcement Learning for 5G-V2V Communication","created":"2020-10-11","cited_by_count":1}],"next_cursor":null}