{"list":"other","total":56,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"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":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"1703.06114","title":"Deep Sets","created":"2017-03-10","cited_by_count":1421},{"id":"2002.00444","title":"Deep Reinforcement Learning for Autonomous Driving: A Survey","created":"2020-02-02","cited_by_count":721},{"id":"2005.04259","title":"VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation","created":"2020-05-08","cited_by_count":530},{"id":"1712.05889","title":"Ray: A Distributed Framework for Emerging AI Applications","created":"2017-12-16","cited_by_count":527},{"id":"1703.02702","title":"Robust Adversarial Reinforcement Learning","created":"2017-03-08","cited_by_count":451},{"id":"1912.12294","title":"Learning by Cheating","created":"2019-12-27","cited_by_count":383},{"id":"2007.13732","title":"Learning Lane Graph Representations for Motion Forecasting","created":"2020-07-27","cited_by_count":382},{"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":"2008.08294","title":"TNT: Target-driveN Trajectory Prediction","created":"2020-08-19","cited_by_count":347},{"id":"2108.09640","title":"DenseTNT: End-to-end Trajectory Prediction from Dense Goal Sets","created":"2021-08-22","cited_by_count":295},{"id":"2109.12674","title":"MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning","created":"2021-09-26","cited_by_count":290},{"id":"1502.02259","title":"Contextual Markov Decision Processes","created":"2015-02-08","cited_by_count":220},{"id":"2102.02915","title":"How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned","created":"2021-02-04","cited_by_count":213},{"id":"2101.06557","title":"TrafficSim: Learning to Simulate Realistic Multi-Agent Behaviors","created":"2021-01-17","cited_by_count":193},{"id":"1911.10868","title":"End-to-End Model-Free Reinforcement Learning for Urban Driving using Implicit Affordances","created":"2019-11-25","cited_by_count":149},{"id":"1610.01283","title":"EPOpt: Learning Robust Neural Network Policies Using Model Ensembles","created":"2016-10-05","cited_by_count":138},{"id":"1810.12282","title":"Assessing Generalization in Deep Reinforcement Learning","created":"2018-10-29","cited_by_count":133},{"id":"1904.09503","title":"Model-free Deep Reinforcement Learning for Urban Autonomous Driving","created":"2019-04-20","cited_by_count":98},{"id":"1810.06544","title":"Deep Imitative Models for Flexible Inference, Planning, and Control","created":"2018-10-15","cited_by_count":76},{"id":"2008.01976","title":"Robust Deep Reinforcement Learning through Adversarial Loss","created":"2020-08-05","cited_by_count":75},{"id":"1710.05465","title":"Flow: A Modular Learning Framework for Mixed Autonomy Traffic","created":"2017-10-16","cited_by_count":73},{"id":"2008.01825","title":"Robust Reinforcement Learning using Adversarial Populations","created":"2020-08-04","cited_by_count":66},{"id":"1904.00511","title":"Risk Averse Robust Adversarial Reinforcement Learning","created":"2019-03-31","cited_by_count":57},{"id":"1911.04175","title":"Multi-Agent Connected Autonomous Driving using Deep Reinforcement Learning","created":"2019-11-11","cited_by_count":53},{"id":"1705.01693","title":"Dissipation of stop-and-go waves via control of autonomous vehicles: Field experiments","created":"2017-05-04","cited_by_count":45},{"id":"2004.06531","title":"Adversarial Evaluation of Autonomous Vehicles in Lane-Change Scenarios","created":"2020-04-14","cited_by_count":43},{"id":"1911.04074","title":"SUMMIT: A Simulator for Urban Driving in Massive Mixed Traffic","created":"2019-11-11","cited_by_count":40},{"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":"1909.06710","title":"Driving in Dense Traffic with Model-Free Reinforcement Learning","created":"2019-09-15","cited_by_count":35},{"id":"2110.13827","title":"Learning to Simulate Self-Driven Particles System with Coordinated Policy Optimization","created":"2021-10-26","cited_by_count":33},{"id":"2107.00200","title":"Social Coordination and Altruism in Autonomous Driving","created":"2021-07-01","cited_by_count":28},{"id":"2202.09514","title":"Robust Reinforcement Learning as a Stackelberg Game via Adaptively-Regularized Adversarial Training","created":"2022-02-19","cited_by_count":28},{"id":"1906.11021","title":"Cooperation-Aware Reinforcement Learning for Merging in Dense Traffic","created":"2019-06-26","cited_by_count":20},{"id":"2207.05853","title":"Interaction-aware Decision-making for Automated Vehicles using Social Value Orientation","created":"2022-07-12","cited_by_count":20},{"id":"1902.07015","title":"Investigating Generalisation in Continuous Deep Reinforcement Learning","created":"2019-02-19","cited_by_count":18},{"id":"2107.00898","title":"Cooperative Autonomous Vehicles that Sympathize with Human Drivers","created":"2021-07-02","cited_by_count":18},{"id":"2005.03863","title":"Learning hierarchical behavior and motion planning for autonomous driving","created":"2020-05-08","cited_by_count":15},{"id":"1905.12197","title":"LeTS-Drive: Driving in a Crowd by Learning from Tree Search","created":"2019-05-29","cited_by_count":13},{"id":"2002.05502","title":"Improving Generalization of Reinforcement Learning with Minimax Distributional Soft Actor-Critic","created":"2020-02-13","cited_by_count":12},{"id":"2103.00058","title":"Scalable Multiagent Driving Policies For Reducing Traffic Congestion","created":"2021-02-26","cited_by_count":11},{"id":"2107.05664","title":"Altruistic Maneuver Planning for Cooperative Autonomous Vehicles Using Multi-agent Advantage Actor-Critic","created":"2021-07-12","cited_by_count":11},{"id":"2005.11895","title":"Reinforcement Learning with Iterative Reasoning for Merging in Dense Traffic","created":"2020-05-25","cited_by_count":10},{"id":"2010.10393","title":"Imitation Learning of Hierarchical Driving Model: from Continuous Intention to Continuous Trajectory","created":"2020-10-20","cited_by_count":8},{"id":"2011.10753","title":"Emergent Road Rules In Multi-Agent Driving Environments","created":"2020-11-21","cited_by_count":8},{"id":"1906.01566","title":"GAMMA: A General Agent Motion Model for Autonomous Driving","created":"2019-06-04","cited_by_count":7},{"id":"1812.09544","title":"Smoothing Traffic Flow via Control of Autonomous Vehicles","created":"2018-12-22","cited_by_count":6},{"id":"2011.13098","title":"An End-to-end Deep Reinforcement Learning Approach for the Long-term Short-term Planning on the Frenet Space","created":"2020-11-26","cited_by_count":5},{"id":"2109.13858","title":"Domain Generalization for Vision-based Driving Trajectory Generation","created":"2021-09-22","cited_by_count":4},{"id":"2112.03759","title":"Learning a Robust Multiagent Driving Policy for Traffic Congestion Reduction","created":"2021-12-03","cited_by_count":4}],"next_cursor":null}