{"list":"other","total":60,"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":"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":"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":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"1606.04671","title":"Progressive Neural Networks","created":"2016-06-15","cited_by_count":1361},{"id":"1504.00702","title":"End-to-End Training of Deep Visuomotor Policies","created":"2015-04-02","cited_by_count":875},{"id":"1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","created":"2017-10-06","cited_by_count":786},{"id":"1511.06581","title":"Dueling Network Architectures for Deep Reinforcement Learning","created":"2015-11-20","cited_by_count":785},{"id":"2002.00444","title":"Deep Reinforcement Learning for Autonomous Driving: A Survey","created":"2020-02-02","cited_by_count":721},{"id":"1710.09829","title":"Dynamic Routing Between Capsules","created":"2017-10-26","cited_by_count":689},{"id":"1705.05065","title":"AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles","created":"2017-05-15","cited_by_count":523},{"id":"1708.05866","title":"A Brief Survey of Deep Reinforcement Learning","created":"2017-08-19","cited_by_count":483},{"id":"1811.10092","title":"Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation","created":"2018-11-25","cited_by_count":305},{"id":"1706.10295","title":"Noisy Networks for Exploration","created":"2017-06-30","cited_by_count":266},{"id":"1802.05438","title":"Mean Field Multi-Agent Reinforcement Learning","created":"2018-02-15","cited_by_count":207},{"id":"1903.04527","title":"Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Control","created":"2019-03-11","cited_by_count":164},{"id":"1707.08475","title":"DARLA: Improving Zero-Shot Transfer in Reinforcement Learning","created":"2017-07-26","cited_by_count":149},{"id":"1905.05717","title":"CoLight: Learning Network-level Cooperation for Traffic Signal Control","created":"2019-05-11","cited_by_count":138},{"id":"1905.05217","title":"CityFlow: A Multi-Agent Reinforcement Learning Environment for Large Scale City Traffic Scenario","created":"2019-05-13","cited_by_count":115},{"id":"2001.11231","title":"Survey of Deep Reinforcement Learning for Motion Planning of Autonomous Vehicles","created":"2020-01-30","cited_by_count":110},{"id":"2005.00935","title":"Deep Reinforcement Learning for Intelligent Transportation Systems: A Survey","created":"2020-05-02","cited_by_count":98},{"id":"1905.04722","title":"Learning Phase Competition for Traffic Signal Control","created":"2019-05-12","cited_by_count":87},{"id":"1710.11622","title":"Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithm","created":"2017-10-31","cited_by_count":65},{"id":"2101.01993","title":"A Survey of Deep RL and IL for Autonomous Driving Policy Learning","created":"2021-01-06","cited_by_count":61},{"id":"1902.00089","title":"Safe, Efficient, and Comfortable Velocity Control based on Reinforcement Learning for Autonomous Driving","created":"2019-01-29","cited_by_count":59},{"id":"1901.11454","title":"Efficient Ridesharing Order Dispatching with Mean Field Multi-Agent Reinforcement Learning","created":"2019-01-31","cited_by_count":57},{"id":"1903.03882","title":"DeepPool: Distributed Model-free Algorithm for Ride-sharing using Deep Reinforcement Learning","created":"2019-03-09","cited_by_count":54},{"id":"1611.06256","title":"Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU","created":"2016-11-18","cited_by_count":48},{"id":"1901.00569","title":"Human-Like Autonomous Car-Following Model with Deep Reinforcement Learning","created":"2019-01-03","cited_by_count":48},{"id":"2106.04493","title":"A Deep Value-network Based Approach for Multi-Driver Order Dispatching","created":"2021-06-08","cited_by_count":45},{"id":"1903.10654","title":"Failure-Scenario Maker for Rule-Based Agent using Multi-agent Adversarial Reinforcement Learning and its Application to Autonomous Driving","created":"2019-03-26","cited_by_count":36},{"id":"2105.01099","title":"Reinforcement Learning for Ridesharing: An Extended Survey","created":"2021-05-03","cited_by_count":35},{"id":"1704.08883","title":"Traffic Light Control Using Deep Policy-Gradient and Value-Function Based Reinforcement Learning","created":"2017-04-28","cited_by_count":33},{"id":"2002.05513","title":"Multi-Vehicle Routing Problems with Soft Time Windows: A Multi-Agent Reinforcement Learning Approach","created":"2020-02-13","cited_by_count":30},{"id":"1911.11260","title":"Deep Reinforcement Learning for Multi-Driver Vehicle Dispatching and Repositioning Problem","created":"2019-11-25","cited_by_count":29},{"id":"1910.02591","title":"Multi-Agent Reinforcement Learning for Order-dispatching via Order-Vehicle Distribution Matching","created":"2019-10-07","cited_by_count":26},{"id":"2010.02068","title":"Deep Reinforcement Learning for Electric Vehicle Routing Problem with Time Windows","created":"2020-10-05","cited_by_count":25},{"id":"1804.04758","title":"MOVI: A Model-Free Approach to Dynamic Fleet Management","created":"2018-04-13","cited_by_count":23},{"id":"1905.11353","title":"CoRide: Joint Order Dispatching and Fleet Management for Multi-Scale Ride-Hailing Platforms","created":"2019-05-27","cited_by_count":22},{"id":"2003.05738","title":"IG-RL: Inductive Graph Reinforcement Learning for Massive-Scale Traffic Signal Control","created":"2020-03-06","cited_by_count":22},{"id":"1709.06656","title":"Deep Reinforcement Learning for Event-Driven Multi-Agent Decision Processes","created":"2017-09-19","cited_by_count":21},{"id":"1610.02891","title":"Personalizing a Dialogue System with Transfer Reinforcement Learning","created":"2016-10-10","cited_by_count":17},{"id":"2009.08052","title":"GeneraLight: Improving Environment Generalization of Traffic Signal Control via Meta Reinforcement Learning","created":"2020-09-17","cited_by_count":17},{"id":"1701.08832","title":"Expert Level control of Ramp Metering based on Multi-task Deep Reinforcement Learning","created":"2017-01-30","cited_by_count":16},{"id":"1804.06264","title":"Automated vehicle's behavior decision making using deep reinforcement learning and high-fidelity simulation environment","created":"2018-04-17","cited_by_count":16},{"id":"1802.04592","title":"A Deep Reinforcement Learning Framework for Rebalancing Dockless Bike Sharing Systems","created":"2018-02-13","cited_by_count":13},{"id":"2002.06723","title":"Reward Design for Driver Repositioning Using Multi-Agent Reinforcement Learning","created":"2020-02-17","cited_by_count":12},{"id":"2104.09936","title":"Network-wide traffic signal control optimization using a multi-agent deep reinforcement learning","created":"2021-04-20","cited_by_count":12},{"id":"1807.01628","title":"Using Reinforcement Learning with Partial Vehicle Detection for Intelligent Traffic Signal Control","created":"2018-07-04","cited_by_count":10},{"id":"1805.02363","title":"Planning and Learning with Stochastic Action Sets","created":"2018-05-07","cited_by_count":9},{"id":"1802.08311","title":"Structured Control Nets for Deep Reinforcement Learning","created":"2018-02-22","cited_by_count":8},{"id":"1909.04760","title":"Deep Reinforcement Learning Algorithm for Dynamic Pricing of Express Lanes with Multiple Access Locations","created":"2019-09-10","cited_by_count":8},{"id":"1804.02884","title":"Policy Gradient With Value Function Approximation For Collective Multiagent Planning","created":"2018-04-09","cited_by_count":6},{"id":"2007.13699","title":"FlexPool: A Distributed Model-Free Deep Reinforcement Learning Algorithm for Joint Passengers & Goods Transportation","created":"2020-07-27","cited_by_count":6},{"id":"1612.05910","title":"Multi-scale Perimeter Control Approach in a Connected-Vehicle Environment","created":"2016-12-18","cited_by_count":5},{"id":"2209.05726","title":"Data efficient reinforcement learning and adaptive optimal perimeter control of network traffic dynamics","created":"2022-09-13","cited_by_count":5},{"id":"1906.01772","title":"Reinforcement Learning When All Actions are Not Always Available","created":"2019-06-05","cited_by_count":3}],"next_cursor":null}