{"list":"other","total":54,"rows":[{"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":"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":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"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":"1911.08265","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","created":"2019-11-19","cited_by_count":1353},{"id":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"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":"1903.00374","title":"Model-Based Reinforcement Learning for Atari","created":"2019-03-01","cited_by_count":502},{"id":"1708.05866","title":"A Brief Survey of Deep Reinforcement Learning","created":"2017-08-19","cited_by_count":483},{"id":"1710.10044","title":"Distributional Reinforcement Learning with Quantile Regression","created":"2017-10-27","cited_by_count":474},{"id":"2108.06266","title":"Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning","created":"2021-08-13","cited_by_count":371},{"id":"1806.06923","title":"Implicit Quantile Networks for Distributional Reinforcement Learning","created":"2018-06-14","cited_by_count":369},{"id":"1701.07274","title":"Deep Reinforcement Learning: An Overview","created":"2017-01-25","cited_by_count":333},{"id":"1610.03295","title":"Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving","created":"2016-10-11","cited_by_count":311},{"id":"1812.03201","title":"Residual Reinforcement Learning for Robot Control","created":"2018-12-07","cited_by_count":274},{"id":"1706.10295","title":"Noisy Networks for Exploration","created":"2017-06-30","cited_by_count":266},{"id":"1807.01281","title":"Human-level performance in first-person multiplayer games with population-based deep reinforcement learning","created":"2018-07-03","cited_by_count":264},{"id":"1704.02532","title":"Deep Reinforcement Learning framework for Autonomous Driving","created":"2017-04-08","cited_by_count":225},{"id":"1901.00137","title":"A Theoretical Analysis of Deep Q-Learning","created":"2019-01-01","cited_by_count":215},{"id":"1802.05438","title":"Mean Field Multi-Agent Reinforcement Learning","created":"2018-02-15","cited_by_count":207},{"id":"2105.04387","title":"Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey","created":"2021-05-10","cited_by_count":130},{"id":"1905.04071","title":"Survey on Evaluation Methods for Dialogue Systems","created":"2019-05-10","cited_by_count":126},{"id":"1904.09503","title":"Model-free Deep Reinforcement Learning for Urban Autonomous Driving","created":"2019-04-20","cited_by_count":98},{"id":"1609.05521","title":"Playing FPS Games with Deep Reinforcement Learning","created":"2016-09-18","cited_by_count":95},{"id":"2112.11561","title":"Explainable Artificial Intelligence for Autonomous Driving: A Comprehensive Overview and Field Guide for Future Research Directions","created":"2021-12-21","cited_by_count":73},{"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":"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":"2006.05779","title":"Self-Supervised Reinforcement Learning for Recommender Systems","created":"2020-06-10","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":"1911.04448","title":"Real-Time Reinforcement Learning","created":"2019-11-11","cited_by_count":40},{"id":"1911.08842","title":"Neural Approximate Dynamic Programming for On-Demand Ride-Pooling","created":"2019-11-20","cited_by_count":33},{"id":"1707.01891","title":"Trust-PCL: An Off-Policy Trust Region Method for Continuous Control","created":"2017-07-06","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":"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":"1803.07250","title":"Cooperative and Distributed Reinforcement Learning of Drones for Field Coverage","created":"2018-03-20","cited_by_count":20},{"id":"2010.01755","title":"A Distributed Model-Free Ride-Sharing Approach for Joint Matching, Pricing, and Dispatching using Deep Reinforcement Learning","created":"2020-10-05","cited_by_count":17},{"id":"1910.14002","title":"A Distributed Model-Free Algorithm for Multi-hop Ride-sharing using Deep Reinforcement Learning","created":"2019-10-30","cited_by_count":11},{"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":"1605.05365","title":"Dynamic Frame skip Deep Q Network","created":"2016-05-17","cited_by_count":5},{"id":"2102.09137","title":"Multi-Agent Reinforcement Learning of 3D Furniture Layout Simulation in Indoor Graphics Scenes","created":"2021-02-18","cited_by_count":5},{"id":"2104.12000","title":"A Deep Reinforcement Learning Approach for the Meal Delivery Problem","created":"2021-04-24","cited_by_count":5},{"id":"1907.06479","title":"Proximal Policy Optimization with Mixed Distributed Training","created":"2019-07-15","cited_by_count":4},{"id":"2007.05783","title":"Simulating multi-exit evacuation using deep reinforcement learning","created":"2020-07-11","cited_by_count":2},{"id":"2108.07772","title":"Optimal Placement of Public Electric Vehicle Charging Stations Using Deep Reinforcement Learning","created":"2021-08-17","cited_by_count":2},{"id":"2206.06011","title":"Reinforcement Learning-based Placement of Charging Stations in Urban Road Networks","created":"2022-06-13","cited_by_count":2},{"id":"2004.11248","title":"A branch-and-Benders-cut algorithm for a bi-objective stochastic facility location problem","created":"2020-04-22","cited_by_count":1}],"next_cursor":null}