{"list":"other","total":67,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"2312.14150","title":"DriveLM: Driving with Graph Visual Question Answering","created":"2023-12-21","cited_by_count":536},{"id":"2306.16927","title":"End-to-end Autonomous Driving: Challenges and Frontiers","created":"2023-06-29","cited_by_count":490},{"id":"2205.15997","title":"TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving","created":"2022-05-31","cited_by_count":485},{"id":"2201.08117","title":"Learning robust perceptive locomotion for quadrupedal robots in the wild","created":"2022-01-20","cited_by_count":382},{"id":"1911.00357","title":"DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames","created":"2019-11-01","cited_by_count":362},{"id":"1807.00412","title":"Learning to Drive in a Day","created":"2018-07-01","cited_by_count":273},{"id":"2206.08129","title":"Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline","created":"2022-06-16","cited_by_count":248},{"id":"2306.07962","title":"Parting with Misconceptions about Learning-based Vehicle Motion Planning","created":"2023-06-13","cited_by_count":242},{"id":"2108.08265","title":"End-to-End Urban Driving by Imitating a Reinforcement Learning Coach","created":"2021-08-18","cited_by_count":194},{"id":"2303.01486","title":"Understanding plasticity in neural networks","created":"2023-03-02","cited_by_count":174},{"id":"2305.06242","title":"Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Driving","created":"2023-05-10","cited_by_count":169},{"id":"2310.08710","title":"Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research","created":"2023-10-12","cited_by_count":160},{"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":"2308.00398","title":"DriveAdapter: Breaking the Coupling Barrier of Perception and Planning in End-to-End Autonomous Driving","created":"2023-08-01","cited_by_count":144},{"id":"2501.15564","title":"Diffusion-Based Planning for Autonomous Driving with Flexible Guidance","created":"2025-01-26","cited_by_count":141},{"id":"2203.11934","title":"Learning from All Vehicles","created":"2022-03-22","cited_by_count":135},{"id":"2212.11419","title":"Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios","created":"2022-12-21","cited_by_count":129},{"id":"2109.13333","title":"Urban Driver: Learning to Drive from Real-world Demonstrations Using Policy Gradients","created":"2021-09-27","cited_by_count":122},{"id":"2210.14222","title":"PlanT: Explainable Planning Transformers via Object-Level Representations","created":"2022-10-25","cited_by_count":105},{"id":"2104.13906","title":"Reward (Mis)design for Autonomous Driving","created":"2021-04-28","cited_by_count":104},{"id":"2403.04133","title":"Towards learning-based planning:The nuPlan benchmark for real-world autonomous driving","created":"2024-03-07","cited_by_count":104},{"id":"1807.03776","title":"CIRL: Controllable Imitative Reinforcement Learning for Vision-based Self-driving","created":"2018-07-10","cited_by_count":97},{"id":"2204.13683","title":"KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients","created":"2022-04-28","cited_by_count":96},{"id":"2306.07957","title":"Hidden Biases of End-to-End Driving Models","created":"2023-06-13","cited_by_count":96},{"id":"1708.04133","title":"Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control","created":"2017-08-10","cited_by_count":93},{"id":"2006.11751","title":"Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learning","created":"2020-06-21","cited_by_count":93},{"id":"2404.14327","title":"PLUTO: Pushing the Limit of Imitation Learning-based Planning for Autonomous Driving","created":"2024-04-22","cited_by_count":84},{"id":"2207.10422","title":"Differentiable Integrated Motion Prediction and Planning with Learnable Cost Function for Autonomous Driving","created":"2022-07-21","cited_by_count":73},{"id":"2502.03349","title":"Robust Autonomy Emerges from Self-Play","created":"2025-02-05","cited_by_count":67},{"id":"2008.07971","title":"Super-Human Performance in Gran Turismo Sport Using Deep Reinforcement Learning","created":"2020-08-18","cited_by_count":65},{"id":"2206.10558","title":"EnvPool: A Highly Parallel Reinforcement Learning Environment Execution Engine","created":"2022-06-21","cited_by_count":62},{"id":"2111.08575","title":"GRI: General Reinforced Imitation and its Application to Vision-Based Autonomous Driving","created":"2021-11-16","cited_by_count":60},{"id":"2406.20083","title":"PoliFormer: Scaling On-Policy RL with Transformers Results in Masterful Navigators","created":"2024-06-28","cited_by_count":58},{"id":"2502.20396","title":"Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids","created":"2025-02-27","cited_by_count":48},{"id":"2103.14666","title":"Autonomous Overtaking in Gran Turismo Sport Using Curriculum Reinforcement Learning","created":"2021-03-26","cited_by_count":45},{"id":"2302.07753","title":"From Prediction to Planning With Goal Conditioned Lane Graph Traversals","created":"2023-02-15","cited_by_count":45},{"id":"2408.01584","title":"GPUDrive: Data-driven, multi-agent driving simulation at 1 million FPS","created":"2024-08-02","cited_by_count":45},{"id":"2005.10091","title":"Label Efficient Visual Abstractions for Autonomous Driving","created":"2020-05-20","cited_by_count":33},{"id":"2412.09602","title":"Hidden Biases of End-to-End Driving Datasets","created":"2024-12-12","cited_by_count":30},{"id":"2306.15713","title":"Rethinking Closed-loop Training for Autonomous Driving","created":"2023-06-27","cited_by_count":29},{"id":"2405.00662","title":"No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO","created":"2024-05-01","cited_by_count":27},{"id":"2405.19153","title":"A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning","created":"2024-05-29","cited_by_count":26},{"id":"2410.15774","title":"Generalizing Motion Planners with Mixture of Experts for Autonomous Driving","created":"2024-10-21","cited_by_count":22},{"id":"2401.10314","title":"LangProp: A code optimization framework using Large Language Models applied to driving","created":"2024-01-18","cited_by_count":18},{"id":"1909.03772","title":"A Survey on Reproducibility by Evaluating Deep Reinforcement Learning Algorithms on Real-World Robots","created":"2019-09-09","cited_by_count":12},{"id":"2309.08452","title":"MBAPPE: MCTS-Built-Around Prediction for Planning Explicitly","created":"2023-09-15","cited_by_count":11},{"id":"2111.02202","title":"Proximal Policy Optimization with Continuous Bounded Action Space via the Beta Distribution","created":"2021-11-03","cited_by_count":10},{"id":"2306.08055","title":"Tune As You Scale: Hyperparameter Optimization For Compute Efficient Training","created":"2023-06-13","cited_by_count":9},{"id":"2409.07830","title":"ReGentS: Real-World Safety-Critical Driving Scenario Generation Made Stable","created":"2024-09-12","cited_by_count":8},{"id":"2501.12799","title":"Int2Planner: An Intention-based Multi-modal Motion Planner for Integrated Prediction and Planning","created":"2025-01-22","cited_by_count":7},{"id":"2408.16375","title":"EasyChauffeur: A Baseline Advancing Simplicity and Efficiency on Waymax","created":"2024-08-29","cited_by_count":6},{"id":"2312.08365","title":"An Invitation to Deep Reinforcement Learning","created":"2023-12-13","cited_by_count":5},{"id":"2407.05376","title":"Rethinking Closed-loop Planning Framework for Imitation-based Model Integrating Prediction and Planning","created":"2024-07-07","cited_by_count":1}],"next_cursor":null}