{"list":"other","total":123,"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":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"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":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1606.03476","title":"Generative Adversarial Imitation Learning","created":"2016-06-10","cited_by_count":1597},{"id":"1703.06114","title":"Deep Sets","created":"2017-03-10","cited_by_count":1421},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"id":"1604.07316","title":"End to End Learning for Self-Driving Cars","created":"2016-04-25","cited_by_count":1009},{"id":"1703.02910","title":"Deep Bayesian Active Learning with Image Data","created":"2017-03-08","cited_by_count":819},{"id":"1511.06581","title":"Dueling Network Architectures for Deep Reinforcement Learning","created":"2015-11-20","cited_by_count":785},{"id":"1707.06887","title":"A Distributional Perspective on Reinforcement Learning","created":"2017-07-21","cited_by_count":765},{"id":"2004.04136","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","created":"2020-04-08","cited_by_count":760},{"id":"2002.00444","title":"Deep Reinforcement Learning for Autonomous Driving: A Survey","created":"2020-02-02","cited_by_count":721},{"id":"1803.10892","title":"Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks","created":"2018-03-29","cited_by_count":690},{"id":"1710.11248","title":"Learning Robust Rewards with Adversarial Inverse Reinforcement Learning","created":"2017-10-30","cited_by_count":490},{"id":"1710.02410","title":"End-to-end Driving via Conditional Imitation Learning","created":"2017-10-06","cited_by_count":485},{"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":"1811.06711","title":"An Algorithmic Perspective on Imitation Learning","created":"2018-11-16","cited_by_count":459},{"id":"1808.01974","title":"A Survey on Deep Transfer Learning","created":"2018-08-06","cited_by_count":419},{"id":"1603.00448","title":"Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization","created":"2016-03-01","cited_by_count":406},{"id":"1910.07738","title":"A Survey of Deep Learning Techniques for Autonomous Driving","created":"2019-10-17","cited_by_count":403},{"id":"1812.03079","title":"ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst","created":"2018-12-07","cited_by_count":397},{"id":"1611.05763","title":"Learning to reinforcement learn","created":"2016-11-17","cited_by_count":377},{"id":"1806.06923","title":"Implicit Quantile Networks for Distributional Reinforcement Learning","created":"2018-06-14","cited_by_count":369},{"id":"1609.05143","title":"Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning","created":"2016-09-16","cited_by_count":366},{"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":"2012.13490","title":"Towards Continual Reinforcement Learning: A Review and Perspectives","created":"2020-12-25","cited_by_count":274},{"id":"1807.00412","title":"Learning to Drive in a Day","created":"2018-07-01","cited_by_count":273},{"id":"2009.08319","title":"Decoupling Representation Learning from Reinforcement Learning","created":"2020-09-14","cited_by_count":269},{"id":"1604.07446","title":"A Survey of Motion Planning and Control Techniques for Self-driving Urban Vehicles","created":"2016-04-25","cited_by_count":254},{"id":"1710.04689","title":"Social Attention: Modeling Attention in Human Crowds","created":"2017-10-12","cited_by_count":186},{"id":"1805.12369","title":"Reinforced Continual Learning","created":"2018-05-31","cited_by_count":186},{"id":"1507.04888","title":"Maximum Entropy Deep Inverse Reinforcement Learning","created":"2015-07-17","cited_by_count":176},{"id":"1809.08835","title":"Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning","created":"2018-09-24","cited_by_count":175},{"id":"1611.03852","title":"A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models","created":"2016-11-11","cited_by_count":168},{"id":"1506.02158","title":"Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference","created":"2015-06-06","cited_by_count":159},{"id":"1603.00748","title":"Continuous Deep Q-Learning with Model-based Acceleration","created":"2016-03-02","cited_by_count":157},{"id":"1810.09202","title":"Graph Convolutional Reinforcement Learning","created":"2018-10-22","cited_by_count":152},{"id":"1612.01079","title":"End-to-end Learning of Driving Models from Large-scale Video Datasets","created":"2016-12-04","cited_by_count":148},{"id":"1708.06374","title":"On a Formal Model of Safe and Scalable Self-driving Cars","created":"2017-08-21","cited_by_count":131},{"id":"2003.06404","title":"A Survey of End-to-End Driving: Architectures and Training Methods","created":"2020-03-13","cited_by_count":123},{"id":"1805.01956","title":"Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning","created":"2018-05-04","cited_by_count":111},{"id":"1912.10773","title":"A Survey of Deep Learning Applications to Autonomous Vehicle Control","created":"2019-12-23","cited_by_count":106},{"id":"1904.09503","title":"Model-free Deep Reinforcement Learning for Urban Autonomous Driving","created":"2019-04-20","cited_by_count":98},{"id":"1807.03776","title":"CIRL: Controllable Imitative Reinforcement Learning for Vision-based Self-driving","created":"2018-07-10","cited_by_count":97},{"id":"1701.06699","title":"Imitating Driver Behavior with Generative Adversarial Networks","created":"2017-01-24","cited_by_count":93},{"id":"1804.09364","title":"Driving Policy Transfer via Modularity and Abstraction","created":"2018-04-25","cited_by_count":92},{"id":"1702.01182","title":"Uncertainty-Aware Reinforcement Learning for Collision Avoidance","created":"2017-02-03","cited_by_count":88},{"id":"1707.02747","title":"Robust Imitation of Diverse Behaviors","created":"2017-07-10","cited_by_count":86},{"id":"1605.06450","title":"Query-Efficient Imitation Learning for End-to-End Autonomous Driving","created":"2016-05-20","cited_by_count":84},{"id":"1707.02201","title":"Learning human behaviors from motion capture by adversarial imitation","created":"2017-07-07","cited_by_count":77},{"id":"1511.04143","title":"Deep Reinforcement Learning in Parameterized Action Space","created":"2015-11-13","cited_by_count":68},{"id":"1704.07911","title":"Explaining How a Deep Neural Network Trained with End-to-End Learning Steers a Car","created":"2017-04-25","cited_by_count":66},{"id":"1802.04564","title":"Diversity-Driven Exploration Strategy for Deep Reinforcement Learning","created":"2018-02-13","cited_by_count":65},{"id":"1706.06122","title":"VAIN: Attentional Multi-agent Predictive Modeling","created":"2017-06-19","cited_by_count":53},{"id":"1710.09483","title":"Multimodal Probabilistic Model-Based Planning for Human-Robot Interaction","created":"2017-10-25","cited_by_count":50},{"id":"1803.01044","title":"Multi-Agent Imitation Learning for Driving Simulation","created":"2018-03-02","cited_by_count":50},{"id":"1901.02705","title":"Model-Predictive Policy Learning with Uncertainty Regularization for Driving in Dense Traffic","created":"2019-01-08","cited_by_count":50},{"id":"1910.00399","title":"Safe Reinforcement Learning on Autonomous Vehicles","created":"2019-09-27","cited_by_count":50},{"id":"1903.00640","title":"Deep Imitation Learning for Autonomous Driving in Generic Urban Scenarios with Enhanced Safety","created":"2019-03-02","cited_by_count":49},{"id":"1810.05766","title":"Hierarchical Game-Theoretic Planning for Autonomous Vehicles","created":"2018-10-13","cited_by_count":48},{"id":"1804.07871","title":"A Reinforcement Learning Based Approach for Automated Lane Change Maneuvers","created":"2018-04-21","cited_by_count":46},{"id":"1811.05432","title":"Deep Object-Centric Policies for Autonomous Driving","created":"2018-11-13","cited_by_count":41},{"id":"2002.10544","title":"Provable Representation Learning for Imitation Learning via Bi-level Optimization","created":"2020-02-24","cited_by_count":41},{"id":"1812.03823","title":"Learning to Drive from Simulation without Real World Labels","created":"2018-12-10","cited_by_count":39},{"id":"1803.10056","title":"Automated Speed and Lane Change Decision Making using Deep Reinforcement Learning","created":"2018-03-14","cited_by_count":36},{"id":"1811.11329","title":"Deep Reinforcement Learning for Autonomous Driving","created":"2018-11-28","cited_by_count":36},{"id":"1802.00265","title":"VR-Goggles for Robots: Real-to-sim Domain Adaptation for Visual Control","created":"2018-02-01","cited_by_count":35},{"id":"2006.15061","title":"Intrinsic Reward Driven Imitation Learning via Generative Model","created":"2020-06-26","cited_by_count":35},{"id":"1811.08586","title":"Urban Driving with Multi-Objective Deep Reinforcement Learning","created":"2018-11-21","cited_by_count":30},{"id":"1809.02926","title":"Probabilistic Prediction of Interactive Driving Behavior via Hierarchical Inverse Reinforcement Learning","created":"2018-09-09","cited_by_count":28},{"id":"1904.07189","title":"Reinforcement Learning with Probabilistic Guarantees for Autonomous Driving","created":"2019-04-15","cited_by_count":28},{"id":"1612.04340","title":"End-to-End Deep Reinforcement Learning for Lane Keeping Assist","created":"2016-12-13","cited_by_count":27},{"id":"1803.10158","title":"End-to-End Learning of Driving Models with Surround-View Cameras and Route Planners","created":"2018-03-27","cited_by_count":27},{"id":"1709.02249","title":"Uncertainty-Aware Learning from Demonstration using Mixture Density Networks with Sampling-Free Variance Modeling","created":"2017-09-03","cited_by_count":25},{"id":"1811.03516","title":"Learning from Demonstration in the Wild","created":"2018-11-08","cited_by_count":25},{"id":"1608.08589","title":"Game-Theoretic Modeling of Driver and Vehicle Interactions for Verification and Validation of Autonomous Vehicle Control Systems","created":"2016-08-30","cited_by_count":24},{"id":"1903.05766","title":"Simulating Emergent Properties of Human Driving Behavior Using Multi-Agent Reward Augmented Imitation Learning","created":"2019-03-14","cited_by_count":24},{"id":"1705.01196","title":"Navigating Occluded Intersections with Autonomous Vehicles using Deep Reinforcement Learning","created":"2017-05-02","cited_by_count":21},{"id":"1909.11538","title":"Automated Lane Change Decision Making using Deep Reinforcement Learning in Dynamic and Uncertain Highway Environment","created":"2019-09-18","cited_by_count":21},{"id":"1707.02515","title":"A Fast Integrated Planning and Control Framework for Autonomous Driving via Imitation Learning","created":"2017-07-09","cited_by_count":20},{"id":"1905.02780","title":"Uncertainty-Aware Data Aggregation for Deep Imitation Learning","created":"2019-05-07","cited_by_count":20},{"id":"1906.11021","title":"Cooperation-Aware Reinforcement Learning for Merging in Dense Traffic","created":"2019-06-26","cited_by_count":20},{"id":"1703.07887","title":"Combining Neural Networks and Tree Search for Task and Motion Planning in Challenging Environments","created":"2017-03-22","cited_by_count":19},{"id":"1709.02066","title":"Formulation of Deep Reinforcement Learning Architecture Toward Autonomous Driving for On-Ramp Merge","created":"2017-09-07","cited_by_count":19},{"id":"1702.02302","title":"Autonomous Braking System via Deep Reinforcement Learning","created":"2017-02-08","cited_by_count":18},{"id":"1904.11483","title":"Safe Reinforcement Learning with Scene Decomposition for Navigating Complex Urban Environments","created":"2019-04-25","cited_by_count":18},{"id":"2001.10208","title":"Towards Learning Multi-agent Negotiations via Self-Play","created":"2020-01-28","cited_by_count":17},{"id":"1710.03804","title":"End-to-End Deep Learning for Steering Autonomous Vehicles Considering Temporal Dependencies","created":"2017-10-10","cited_by_count":16}],"next_cursor":"100"}