{"list":"other","total":55,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"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":"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":"1705.10528","title":"Constrained Policy Optimization","created":"2017-05-30","cited_by_count":983},{"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":"1803.08475","title":"Attention, Learn to Solve Routing Problems!","created":"2018-03-22","cited_by_count":656},{"id":"1611.09940","title":"Neural Combinatorial Optimization with Reinforcement Learning","created":"2016-11-29","cited_by_count":608},{"id":"1708.05866","title":"A Brief Survey of Deep Reinforcement Learning","created":"2017-08-19","cited_by_count":483},{"id":"2010.16011","title":"POMO: Policy Optimization with Multiple Optima for Reinforcement Learning","created":"2020-10-30","cited_by_count":348},{"id":"1701.07274","title":"Deep Reinforcement Learning: An Overview","created":"2017-01-25","cited_by_count":333},{"id":"1802.04240","title":"Reinforcement Learning for Solving the Vehicle Routing Problem","created":"2018-02-12","cited_by_count":333},{"id":"1906.01227","title":"An Efficient Graph Convolutional Network Technique for the Travelling Salesman Problem","created":"2019-06-04","cited_by_count":269},{"id":"2009.07888","title":"Transfer Learning in Deep Reinforcement Learning: A Survey","created":"2020-09-16","cited_by_count":265},{"id":"2003.03600","title":"Reinforcement Learning for Combinatorial Optimization: A Survey","created":"2020-03-07","cited_by_count":236},{"id":"1802.05438","title":"Mean Field Multi-Agent Reinforcement Learning","created":"2018-02-15","cited_by_count":207},{"id":"1611.01224","title":"Sample Efficient Actor-Critic with Experience Replay","created":"2016-11-03","cited_by_count":188},{"id":"1810.00337","title":"Learning to Perform Local Rewriting for Combinatorial Optimization","created":"2018-09-30","cited_by_count":185},{"id":"1511.08779","title":"Multiagent Cooperation and Competition with Deep Reinforcement Learning","created":"2015-11-27","cited_by_count":184},{"id":"1802.07245","title":"Meta-Reinforcement Learning of Structured Exploration Strategies","created":"2018-02-20","cited_by_count":130},{"id":"1811.08359","title":"Strong mixed-integer programming formulations for trained neural networks","created":"2018-11-20","cited_by_count":115},{"id":"2012.10638","title":"Multi-Decoder Attention Model with Embedding Glimpse for Solving Vehicle Routing Problems","created":"2020-12-19","cited_by_count":100},{"id":"2106.05126","title":"Efficient Active Search for Combinatorial Optimization Problems","created":"2021-06-09","cited_by_count":100},{"id":"2005.00935","title":"Deep Reinforcement Learning for Intelligent Transportation Systems: A Survey","created":"2020-05-02","cited_by_count":98},{"id":"2010.12001","title":"Reinforcement Learning with Combinatorial Actions: An Application to Vehicle Routing","created":"2020-10-22","cited_by_count":61},{"id":"1906.09323","title":"Reinforcement Learning with Convex Constraints","created":"2019-06-21","cited_by_count":60},{"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":"1512.04860","title":"Increasing the Action Gap: New Operators for Reinforcement Learning","created":"2015-12-15","cited_by_count":49},{"id":"2106.04493","title":"A Deep Value-network Based Approach for Multi-Driver Order Dispatching","created":"2021-06-08","cited_by_count":45},{"id":"1911.08842","title":"Neural Approximate Dynamic Programming for On-Demand Ride-Pooling","created":"2019-11-20","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":"2006.09100","title":"Learning to Solve Vehicle Routing Problems with Time Windows through Joint Attention","created":"2020-06-16","cited_by_count":29},{"id":"1706.07450","title":"Revised Note on Learning Algorithms for Quadratic Assignment with Graph Neural Networks","created":"2017-06-22","cited_by_count":28},{"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":"1602.02672","title":"Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks","created":"2016-02-08","cited_by_count":21},{"id":"2102.07359","title":"Intelligent Electric Vehicle Charging Recommendation Based on Multi-Agent Reinforcement Learning","created":"2021-02-15","cited_by_count":20},{"id":"2105.08791","title":"Value Function is All You Need: A Unified Learning Framework for Ride Hailing Platforms","created":"2021-05-18","cited_by_count":16},{"id":"2105.12899","title":"Learning to Optimize Industry-Scale Dynamic Pickup and Delivery Problems","created":"2021-05-27","cited_by_count":15},{"id":"2002.06723","title":"Reward Design for Driver Repositioning Using Multi-Agent Reinforcement Learning","created":"2020-02-17","cited_by_count":12},{"id":"2009.14679","title":"Scalable Deep Reinforcement Learning for Ride-Hailing","created":"2020-09-27","cited_by_count":12},{"id":"1811.04345","title":"Optimizing Taxi Carpool Policies via Reinforcement Learning and Spatio-Temporal Mining","created":"2018-11-11","cited_by_count":8},{"id":"1811.07048","title":"Dynamic Type Matching","created":"2018-11-16","cited_by_count":8},{"id":"1903.02716","title":"Can Sophisticated Dispatching Strategy Acquired by Reinforcement Learning? - A Case Study in Dynamic Courier Dispatching System","created":"2019-03-07","cited_by_count":8},{"id":"2010.02369","title":"A Reinforcement Learning Approach for Rebalancing Electric Vehicle Sharing Systems","created":"2020-10-05","cited_by_count":7},{"id":"1811.02644","title":"DeepDPM: Dynamic Population Mapping via Deep Neural Network","created":"2018-10-25","cited_by_count":6}],"next_cursor":null}