{"list":"other","total":72,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"1707.06887","title":"A Distributional Perspective on Reinforcement Learning","created":"2017-07-21","cited_by_count":765},{"id":"1811.06128","title":"Machine Learning for Combinatorial Optimization: a Methodological Tour d'Horizon","created":"2018-11-15","cited_by_count":623},{"id":"1911.10635","title":"Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms","created":"2019-11-24","cited_by_count":567},{"id":"1507.06527","title":"Deep Recurrent Q-Learning for Partially Observable MDPs","created":"2015-07-23","cited_by_count":465},{"id":"1604.06057","title":"Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation","created":"2016-04-20","cited_by_count":286},{"id":"1906.04161","title":"Self-Supervised Exploration via Disagreement","created":"2019-06-10","cited_by_count":265},{"id":"2003.03600","title":"Reinforcement Learning for Combinatorial Optimization: A Survey","created":"2020-03-07","cited_by_count":236},{"id":"1709.04326","title":"Learning with Opponent-Learning Awareness","created":"2017-09-13","cited_by_count":222},{"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":"2001.11231","title":"Survey of Deep Reinforcement Learning for Motion Planning of Autonomous Vehicles","created":"2020-01-30","cited_by_count":110},{"id":"1602.04105","title":"Convolutional Radio Modulation Recognition Networks","created":"2016-02-12","cited_by_count":106},{"id":"2007.08564","title":"Age of Information: An Introduction and Survey","created":"2020-07-16","cited_by_count":70},{"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":"2010.02966","title":"Reinforcement Learning with Random Delays","created":"2020-10-06","cited_by_count":59},{"id":"2203.02878","title":"A Survey for Solving Mixed Integer Programming via Machine Learning","created":"2022-03-06","cited_by_count":44},{"id":"1911.04448","title":"Real-Time Reinforcement Learning","created":"2019-11-11","cited_by_count":40},{"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":"1808.01486","title":"Spatial Deep Learning for Wireless Scheduling","created":"2018-08-04","cited_by_count":32},{"id":"1801.01803","title":"Scheduling Policies for Minimizing Age of Information in Broadcast Wireless Networks","created":"2018-01-05","cited_by_count":22},{"id":"1301.4666","title":"A Linearly Convergent Conditional Gradient Algorithm with Applications to Online and Stochastic Optimization","created":"2013-01-20","cited_by_count":18},{"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":"2105.04196","title":"AoI-Aware Resource Allocation for Platoon-Based C-V2X Networks via Multi-Agent Multi-Task Reinforcement Learning","created":"2021-05-10","cited_by_count":18},{"id":"2203.07345","title":"Federated Cycling (FedCy): Semi-supervised Federated Learning of Surgical Phases","created":"2022-03-14","cited_by_count":18},{"id":"1905.02993","title":"Deep Reinforcement Learning for Minimizing Age-of-Information in UAV-assisted Networks","created":"2019-05-08","cited_by_count":13},{"id":"2406.11245","title":"Deep-Reinforcement-Learning-Based AoI-Aware Resource Allocation for RIS-Aided IoV Networks","created":"2024-06-17","cited_by_count":13},{"id":"1812.08286","title":"On the Role of Age of Information in the Internet of Things","created":"2018-12-19","cited_by_count":11},{"id":"1506.08637","title":"On The Age Of Information In Status Update Systems With Packet Management","created":"2015-06-29","cited_by_count":10},{"id":"1807.04356","title":"Joint Status Sampling and Updating for Minimizing Age of Information in the Internet of Things","created":"2018-07-11","cited_by_count":10},{"id":"1908.06367","title":"A Reinforcement Learning Framework for Optimizing Age-of-Information in RF-powered Communication Systems","created":"2019-08-18","cited_by_count":10},{"id":"2003.00391","title":"Deep Reinforcement Learning for Fresh Data Collection in UAV-assisted IoT Networks","created":"2020-03-01","cited_by_count":10},{"id":"2009.04224","title":"AoI Minimization in Status Update Control with Energy Harvesting Sensors","created":"2020-09-09","cited_by_count":10},{"id":"2104.01527","title":"Distributed Reinforcement Learning for Age of Information Minimization in Real-Time IoT Systems","created":"2021-04-04","cited_by_count":10},{"id":"2003.04816","title":"Data Freshness and Energy-Efficient UAV Navigation Optimization: A Deep Reinforcement Learning Approach","created":"2020-02-21","cited_by_count":9},{"id":"2012.14137","title":"Federated Multi-Agent Actor-Critic Learning for Age Sensitive Mobile Edge Computing","created":"2020-12-28","cited_by_count":9},{"id":"2301.03423","title":"Multi-UAV Path Learning for Age and Power Optimization in IoT with UAV Battery Recharge","created":"2023-01-09","cited_by_count":9},{"id":"2301.04298","title":"Age of Information in Deep Learning-Driven Task-Oriented Communications","created":"2023-01-11","cited_by_count":9},{"id":"1909.06020","title":"Spectrum Sensing Based on Deep Learning Classification for Cognitive Radios","created":"2019-09-13","cited_by_count":8},{"id":"2312.00279","title":"Age-Based Scheduling for Mobile Edge Computing: A Deep Reinforcement Learning Approach","created":"2023-12-01","cited_by_count":6},{"id":"1803.06467","title":"Optimizing Information Freshness in Wireless Networks under General Interference Constraints","created":"2018-03-17","cited_by_count":5},{"id":"1902.09467","title":"Reinforcement Learning to Minimize Age of Information with an Energy Harvesting Sensor with HARQ and Sensing Cost","created":"2019-01-24","cited_by_count":5},{"id":"2002.09805","title":"Risk-Aware Optimization of Age of Information in the Internet of Things","created":"2020-02-23","cited_by_count":5},{"id":"2103.00092","title":"The Age of Correlated Features in Supervised Learning based Forecasting","created":"2021-02-27","cited_by_count":5},{"id":"2309.14757","title":"Age Minimization in Massive IoT via UAV Swarm: A Multi-agent Reinforcement Learning Approach","created":"2023-09-26","cited_by_count":5},{"id":"2312.16163","title":"Age of Information in Gossip Networks: A Friendly Introduction and Literature Survey","created":"2023-12-26","cited_by_count":5},{"id":"2405.00056","title":"Age of Information Minimization using Multi-agent UAVs based on AI-Enhanced Mean Field Resource Allocation","created":"2024-04-24","cited_by_count":5},{"id":"1806.00336","title":"A Reinforcement Learning Approach to Age of Information in Multi-User Networks","created":"2018-06-01","cited_by_count":3},{"id":"1811.06776","title":"Reinforcement Learning Based Scheduling Algorithm for Optimizing Age of Information in Ultra Reliable Low Latency Networks","created":"2018-11-16","cited_by_count":3},{"id":"1905.11570","title":"Age Based Task Scheduling and Computation Offloading in Mobile-Edge Computing Systems","created":"2019-05-28","cited_by_count":3},{"id":"2201.12277","title":"On-Demand AoI Minimization in Resource-Constrained Cache-Enabled IoT Networks with Energy Harvesting Sensors","created":"2022-01-28","cited_by_count":3},{"id":"2208.06948","title":"How Does Data Freshness Affect Real-time Supervised Learning?","created":"2022-08-15","cited_by_count":3},{"id":"2311.13861","title":"A Deep Reinforcement Learning Approach for Improving Age of Information in Mission-Critical IoT","created":"2023-11-23","cited_by_count":3},{"id":"2406.02139","title":"Statistical Age of Information: A Risk-Aware Metric and Its Applications in Status Updates","created":"2024-06-04","cited_by_count":3},{"id":"1906.00192","title":"Closed-Form Analysis of Non-Linear Age-of-Information in Status Updates with an Energy Harvesting Transmitter","created":"2019-06-01","cited_by_count":2},{"id":"2007.04072","title":"Optimizing Information Freshness via Multiuser Scheduling with Adaptive NOMA/OMA","created":"2020-07-07","cited_by_count":2},{"id":"2101.10225","title":"Age Debt: A General Framework For Minimizing Age of Information","created":"2021-01-25","cited_by_count":2},{"id":"2111.02309","title":"Pull or Wait: How to Optimize Query Age of Information","created":"2021-11-03","cited_by_count":2},{"id":"2201.02787","title":"Age-of-information minimization via opportunistic sampling by an energy harvesting source","created":"2022-01-08","cited_by_count":2},{"id":"2210.15672","title":"Average Age of Information Penalty of Short-Packet Communications with Packet Management","created":"2022-10-26","cited_by_count":2},{"id":"2501.14603","title":"Age and Power Minimization via Meta-Deep Reinforcement Learning in UAV Networks","created":"2025-01-24","cited_by_count":2},{"id":"1803.06469","title":"Distributed Scheduling Algorithms for Optimizing Information Freshness in Wireless Networks","created":"2018-03-17","cited_by_count":1},{"id":"1811.12924","title":"Joint Information Freshness and Completion Time Optimization for Vehicular Networks","created":"2018-11-30","cited_by_count":1},{"id":"1901.05428","title":"Relative Age of Information: A New Metric for Status Update Systems","created":"2019-01-16","cited_by_count":1},{"id":"2012.13663","title":"Analyzing Age of Information in Multiaccess Networks by Fluid Limits","created":"2020-12-26","cited_by_count":1},{"id":"2202.09222","title":"Improving AoI via Learning-based Distributed MAC in Wireless Networks","created":"2022-02-18","cited_by_count":1},{"id":"2212.13390","title":"Hierarchical Deep Reinforcement Learning for Age-of-Information Minimization in IRS-aided and Wireless-powered Wireless Networks","created":"2022-12-27","cited_by_count":1},{"id":"2304.07813","title":"Deep Reinforcement Learning-Assisted Age-optimal Transmission Policy for HARQ-aided NOMA Networks","created":"2023-04-16","cited_by_count":1},{"id":"2309.02913","title":"Ensemble DNN for Age-of-Information Minimization in UAV-assisted Networks","created":"2023-09-06","cited_by_count":1},{"id":"2401.04904","title":"Scalable Cyclic Schedulers for Age of Information Optimization in Large-Scale Status Update Systems","created":"2024-01-10","cited_by_count":1},{"id":"2501.06688","title":"Optimizing Age of Information without Knowing the Age of Information","created":"2025-01-12","cited_by_count":1}],"next_cursor":null}