{"list":"other","total":94,"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":"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":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"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":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"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":"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":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"id":"1610.05492","title":"Federated Learning: Strategies for Improving Communication Efficiency","created":"2016-10-18","cited_by_count":1475},{"id":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942},{"id":"1506.03134","title":"Pointer Networks","created":"2015-06-09","cited_by_count":895},{"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":"1704.01665","title":"Learning Combinatorial Optimization Algorithms over Graphs","created":"2017-04-05","cited_by_count":561},{"id":"1706.05296","title":"Value-Decomposition Networks For Cooperative Multi-Agent Learning","created":"2017-06-16","cited_by_count":503},{"id":"1708.05866","title":"A Brief Survey of Deep Reinforcement Learning","created":"2017-08-19","cited_by_count":483},{"id":"1611.05763","title":"Learning to reinforcement learn","created":"2016-11-17","cited_by_count":377},{"id":"1605.07736","title":"Learning Multiagent Communication with Backpropagation","created":"2016-05-25","cited_by_count":366},{"id":"1711.07553","title":"Residual Gated Graph ConvNets","created":"2017-11-20","cited_by_count":346},{"id":"1701.07274","title":"Deep Reinforcement Learning: An Overview","created":"2017-01-25","cited_by_count":333},{"id":"2007.03964","title":"Responsive Safety in Reinforcement Learning by PID Lagrangian Methods","created":"2020-07-08","cited_by_count":316},{"id":"1906.01227","title":"An Efficient Graph Convolutional Network Technique for the Travelling Salesman Problem","created":"2019-06-04","cited_by_count":269},{"id":"2003.08938","title":"Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations","created":"2020-03-19","cited_by_count":238},{"id":"1301.3836","title":"The Complexity of Decentralized Control of Markov Decision Processes","created":"2013-01-16","cited_by_count":231},{"id":"1905.10083","title":"Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computing","created":"2019-05-24","cited_by_count":228},{"id":"1810.05687","title":"Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience","created":"2018-10-12","cited_by_count":217},{"id":"1704.03165","title":"struc2vec: Learning Node Representations from Structural Identity","created":"2017-04-11","cited_by_count":215},{"id":"2010.03152","title":"Projection-Based Constrained Policy Optimization","created":"2020-10-07","cited_by_count":203},{"id":"1511.08779","title":"Multiagent Cooperation and Competition with Deep Reinforcement Learning","created":"2015-11-27","cited_by_count":184},{"id":"1302.4972","title":"Causal Inference and Causal Explanation with Background Knowledge","created":"2013-02-20","cited_by_count":170},{"id":"1810.07862","title":"Applications of Deep Reinforcement Learning in Communications and Networking: A Survey","created":"2018-10-18","cited_by_count":167},{"id":"1607.07086","title":"An Actor-Critic Algorithm for Sequence Prediction","created":"2016-07-24","cited_by_count":159},{"id":"1603.00748","title":"Continuous Deep Q-Learning with Model-based Acceleration","created":"2016-03-02","cited_by_count":157},{"id":"1803.00101","title":"Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning","created":"2018-02-28","cited_by_count":156},{"id":"2011.05869","title":"CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guarantee","created":"2020-11-11","cited_by_count":134},{"id":"2301.08028","title":"A Tutorial on Meta-Reinforcement Learning","created":"2023-01-19","cited_by_count":108},{"id":"2003.06016","title":"Invariant Causal Prediction for Block MDPs","created":"2020-03-12","cited_by_count":105},{"id":"2111.12444","title":"Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications","created":"2021-11-24","cited_by_count":97},{"id":"1703.10069","title":"Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games","created":"2017-03-29","cited_by_count":96},{"id":"1909.00560","title":"Edge Intelligence: The Confluence of Edge Computing and Artificial Intelligence","created":"2019-09-02","cited_by_count":76},{"id":"2202.06558","title":"Saute RL: Almost Surely Safe Reinforcement Learning Using State Augmentation","created":"2022-02-14","cited_by_count":69},{"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":"1910.01465","title":"Reducing Overestimation Bias in Multi-Agent Domains Using Double Centralized Critics","created":"2019-10-03","cited_by_count":47},{"id":"2102.01420","title":"The Road Towards 6G: A Comprehensive Survey","created":"2021-02-02","cited_by_count":40},{"id":"2011.13464","title":"Meta-learning in natural and artificial intelligence","created":"2020-11-26","cited_by_count":39},{"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":"2209.08025","title":"Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability","created":"2022-09-16","cited_by_count":36},{"id":"2102.05714","title":"Domain Adaptation In Reinforcement Learning Via Latent Unified State Representation","created":"2021-02-10","cited_by_count":35},{"id":"2110.02793","title":"Multi-Agent Constrained Policy Optimisation","created":"2021-10-06","cited_by_count":35},{"id":"2110.13484","title":"Applications of Multi-Agent Reinforcement Learning in Future Internet: A Comprehensive Survey","created":"2021-10-26","cited_by_count":34},{"id":"1912.05744","title":"Artificial Intelligence-Enabled Intelligent 6G Networks","created":"2019-12-12","cited_by_count":28},{"id":"1805.06146","title":"Optimized Computation Offloading Performance in Virtual Edge Computing Systems via Deep Reinforcement Learning","created":"2018-05-16","cited_by_count":26},{"id":"2203.08398","title":"COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks","created":"2022-03-16","cited_by_count":26},{"id":"2102.07247","title":"Reinforcement Learning for IoT Security: A Comprehensive Survey","created":"2021-02-14","cited_by_count":23},{"id":"2005.02459","title":"Deep Reinforcement Learning for Task Offloading in Mobile Edge Computing Systems","created":"2020-04-10","cited_by_count":20},{"id":"1910.09191","title":"Regularization Matters in Policy Optimization","created":"2019-10-21","cited_by_count":13},{"id":"2107.08241","title":"High-Accuracy Model-Based Reinforcement Learning, a Survey","created":"2021-07-17","cited_by_count":13},{"id":"1805.06695","title":"Survey on Multi-Access Edge Computing for Internet of Things Realization","created":"2018-05-17","cited_by_count":12},{"id":"2004.11986","title":"CFR-RL: Traffic Engineering with Reinforcement Learning in SDN","created":"2020-04-24","cited_by_count":12},{"id":"1310.0720","title":"A Survey on Device-to-Device Communication in Cellular Networks","created":"2013-10-02","cited_by_count":10},{"id":"1810.11758","title":"Distributive Dynamic Spectrum Access through Deep Reinforcement Learning: A Reservoir Computing Based Approach","created":"2018-10-28","cited_by_count":10},{"id":"2008.09930","title":"DMRO:A Deep Meta Reinforcement Learning-based Task Offloading Framework for Edge-Cloud Computing","created":"2020-08-23","cited_by_count":8},{"id":"2007.10102","title":"A Machine Learning Approach for Task and Resource Allocation in Mobile Edge Computing Based Networks","created":"2020-07-20","cited_by_count":7},{"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":"2103.14891","title":"KnowRU: Knowledge Reusing via Knowledge Distillation in Multi-agent Reinforcement Learning","created":"2021-03-27","cited_by_count":6},{"id":"1704.02613","title":"Deep Multi-User Reinforcement Learning for Distributed Dynamic Spectrum Access","created":"2017-04-09","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":"2005.08332","title":"Learning-based Prediction, Rendering and Association Optimization for MEC-enabled Wireless Virtual Reality (VR) Network","created":"2020-05-17","cited_by_count":5},{"id":"2102.10498","title":"Customized Slicing for 6G: Enforcing Artificial Intelligence on Resource Management","created":"2021-02-21","cited_by_count":5},{"id":"2104.01036","title":"Hybrid Policy Learning for Energy-Latency Tradeoff in MEC-Assisted VR Video Service","created":"2021-04-02","cited_by_count":5},{"id":"1809.01560","title":"Reinforcement Learning under Threats","created":"2018-09-05","cited_by_count":4},{"id":"2204.02267","title":"Multi-Agent Distributed Reinforcement Learning for Making Decentralized Offloading Decisions","created":"2022-04-05","cited_by_count":4},{"id":"2206.03623","title":"Dap-FL: Federated Learning flourishes by adaptive tuning and secure aggregation","created":"2022-06-08","cited_by_count":4},{"id":"2003.03758","title":"Reinforcement Learning Based Cooperative Coded Caching under Dynamic Popularities in Ultra-Dense Networks","created":"2020-03-08","cited_by_count":3},{"id":"2007.08793","title":"Towards Enabling Critical mMTC: A Review of URLLC within mMTC","created":"2020-07-17","cited_by_count":3},{"id":"2312.10418","title":"Fractional Deep Reinforcement Learning for Age-Minimal Mobile Edge Computing","created":"2023-12-16","cited_by_count":3},{"id":"1904.07961","title":"RL-Based User Association and Resource Allocation for Multi-UAV enabled MEC","created":"2019-04-08","cited_by_count":2},{"id":"2006.11513","title":"Deep Learning based Radio Resource Management in NOMA Networks: User Association, Subchannel and Power Allocation","created":"2020-06-20","cited_by_count":2},{"id":"2103.00428","title":"Cache Placement Optimization in Mobile Edge Computing Networks with Unaware Environment -- An Extended Multi-armed Bandit Approach","created":"2021-02-28","cited_by_count":2},{"id":"2201.11410","title":"Reinforcement Learning-Empowered Mobile Edge Computing for 6G Edge Intelligence","created":"2022-01-27","cited_by_count":2},{"id":"2203.10819","title":"Proximal Policy Optimization-based Transmit Beamforming and Phase-shift Design in an IRS-aided ISAC System for the THz Band","created":"2022-03-21","cited_by_count":2},{"id":"2209.04164","title":"Joint Caching and Transmission in the Mobile Edge Network: A Multi-Agent Learning Approach","created":"2022-09-09","cited_by_count":2},{"id":"1407.3435","title":"Listen-and-Talk: Full-duplex Cognitive Radio Networks","created":"2014-07-13","cited_by_count":1},{"id":"1809.08966","title":"SDN-Based Resource Management for Autonomous Vehicular Networks: A Multi-Access Edge Computing Approach","created":"2018-09-24","cited_by_count":1},{"id":"2002.10577","title":"Dynamic Power Allocation and Virtual Cell Formation for Throughput-Optimal Vehicular Edge Networks in Highway Transportation","created":"2020-02-24","cited_by_count":1},{"id":"2101.10447","title":"Environment-Adaptive Multiple Access for Distributed V2X Network: A Reinforcement Learning Framework","created":"2021-01-03","cited_by_count":1}],"next_cursor":null}