{"list":"other","total":151,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"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":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"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":"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":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"1911.02685","title":"A Comprehensive Survey on Transfer Learning","created":"2019-11-07","cited_by_count":1160},{"id":"1604.07316","title":"End to End Learning for Self-Driving Cars","created":"2016-04-25","cited_by_count":1009},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"2108.10470","title":"Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning","created":"2021-08-24","cited_by_count":998},{"id":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942},{"id":"2302.00487","title":"A Comprehensive Survey of Continual Learning: Theory, Method and Application","created":"2023-01-31","cited_by_count":872},{"id":"2205.13542","title":"BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation","created":"2022-05-26","cited_by_count":850},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"1705.08926","title":"Counterfactual Multi-Agent Policy Gradients","created":"2017-05-24","cited_by_count":751},{"id":"2002.00444","title":"Deep Reinforcement Learning for Autonomous Driving: A Survey","created":"2020-02-02","cited_by_count":721},{"id":"2106.02039","title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","created":"2021-06-03","cited_by_count":644},{"id":"1902.04043","title":"The StarCraft Multi-Agent Challenge","created":"2019-02-11","cited_by_count":597},{"id":"1605.06676","title":"Learning to Communicate with Deep Multi-Agent Reinforcement Learning","created":"2016-05-21","cited_by_count":575},{"id":"1911.10635","title":"Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms","created":"2019-11-24","cited_by_count":567},{"id":"1705.05065","title":"AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles","created":"2017-05-15","cited_by_count":523},{"id":"2106.11810","title":"NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles","created":"2021-06-22","cited_by_count":493},{"id":"2306.16927","title":"End-to-end Autonomous Driving: Challenges and Frontiers","created":"2023-06-29","cited_by_count":490},{"id":"2003.08839","title":"Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","created":"2020-03-19","cited_by_count":485},{"id":"2205.15997","title":"TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving","created":"2022-05-31","cited_by_count":485},{"id":"1708.05866","title":"A Brief Survey of Deep Reinforcement Learning","created":"2017-08-19","cited_by_count":483},{"id":"2203.11496","title":"TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers","created":"2022-03-22","cited_by_count":466},{"id":"2310.01412","title":"DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model","created":"2023-10-02","cited_by_count":461},{"id":"2110.04596","title":"Deep Long-Tailed Learning: A Survey","created":"2021-10-09","cited_by_count":417},{"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":"1605.07736","title":"Learning Multiagent Communication with Backpropagation","created":"2016-05-25","cited_by_count":366},{"id":"2205.13790","title":"BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework","created":"2022-05-27","cited_by_count":336},{"id":"2011.09533","title":"Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?","created":"2020-11-18","cited_by_count":294},{"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":"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":"1910.03088","title":"INTERACTION Dataset: An INTERnational, Adversarial and Cooperative moTION Dataset in Interactive Driving Scenarios with Semantic Maps","created":"2019-09-30","cited_by_count":231},{"id":"1807.11546","title":"Textual Explanations for Self-Driving Vehicles","created":"2018-07-30","cited_by_count":226},{"id":"2108.00941","title":"A Survey of Human-in-the-loop for Machine Learning","created":"2021-08-02","cited_by_count":215},{"id":"2211.07752","title":"Robot Operating System 2: Design, Architecture, and Uses In The Wild","created":"2022-11-14","cited_by_count":199},{"id":"1802.08757","title":"Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents","created":"2018-02-23","cited_by_count":194},{"id":"2203.10642","title":"FUTR3D: A Unified Sensor Fusion Framework for 3D Detection","created":"2022-03-20","cited_by_count":194},{"id":"2101.06557","title":"TrafficSim: Learning to Simulate Realistic Multi-Agent Behaviors","created":"2021-01-17","cited_by_count":193},{"id":"2310.03026","title":"LanguageMPC: Large Language Models as Decision Makers for Autonomous Driving","created":"2023-10-04","cited_by_count":190},{"id":"1409.2329","title":"Recurrent Neural Network Regularization","created":"2014-09-08","cited_by_count":189},{"id":"2003.06709","title":"FACMAC: Factored Multi-Agent Centralised Policy Gradients","created":"2020-03-14","cited_by_count":178},{"id":"1805.07733","title":"Learning Attentional Communication for Multi-Agent Cooperation","created":"2018-05-20","cited_by_count":175},{"id":"1903.04527","title":"Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Control","created":"2019-03-11","cited_by_count":164},{"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":"2202.11762","title":"Safe Control with Learned Certificates: A Survey of Neural Lyapunov, Barrier, and Contraction methods","created":"2022-02-23","cited_by_count":151},{"id":"1703.06182","title":"Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability","created":"2017-03-17","cited_by_count":148},{"id":"2209.15189","title":"Learning by Distilling Context","created":"2022-09-30","cited_by_count":138},{"id":"1812.11794","title":"Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applications","created":"2018-12-31","cited_by_count":127},{"id":"2401.05577","title":"VLP: Vision Language Planning for Autonomous Driving","created":"2024-01-10","cited_by_count":126},{"id":"2010.09776","title":"SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving","created":"2020-10-19","cited_by_count":121},{"id":"1702.08887","title":"Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning","created":"2017-02-28","cited_by_count":117},{"id":"1905.05217","title":"CityFlow: A Multi-Agent Reinforcement Learning Environment for Large Scale City Traffic Scenario","created":"2019-05-13","cited_by_count":115},{"id":"2303.09824","title":"Motion Planning for Autonomous Driving: The State of the Art and Future Perspectives","created":"2023-03-17","cited_by_count":114},{"id":"2310.10943","title":"Reaching the Limit in Autonomous Racing: Optimal Control versus Reinforcement Learning","created":"2023-10-17","cited_by_count":111},{"id":"2001.11231","title":"Survey of Deep Reinforcement Learning for Motion Planning of Autonomous Vehicles","created":"2020-01-30","cited_by_count":110},{"id":"1703.10631","title":"Interpretable Learning for Self-Driving Cars by Visualizing Causal Attention","created":"2017-03-30","cited_by_count":107},{"id":"2210.06609","title":"TrafficGen: Learning to Generate Diverse and Realistic Traffic Scenarios","created":"2022-10-12","cited_by_count":106},{"id":"2203.08975","title":"A Survey of Multi-Agent Deep Reinforcement Learning with Communication","created":"2022-03-16","cited_by_count":104},{"id":"2302.11803","title":"A Comprehensive Survey on Source-free Domain Adaptation","created":"2023-02-23","cited_by_count":104},{"id":"2101.04233","title":"Independent Policy Gradient Methods for Competitive Reinforcement Learning","created":"2021-01-11","cited_by_count":101},{"id":"2309.10228","title":"Drive as You Speak: Enabling Human-Like Interaction with Large Language Models in Autonomous Vehicles","created":"2023-09-19","cited_by_count":100},{"id":"1904.09503","title":"Model-free Deep Reinforcement Learning for Urban Autonomous Driving","created":"2019-04-20","cited_by_count":98},{"id":"2008.06693","title":"Explainability in Deep Reinforcement Learning","created":"2020-08-15","cited_by_count":97},{"id":"1906.04737","title":"Dealing with Non-Stationarity in Multi-Agent Deep Reinforcement Learning","created":"2019-06-11","cited_by_count":93},{"id":"1809.03531","title":"PRIMAL: Pathfinding via Reinforcement and Imitation Multi-Agent Learning","created":"2018-09-10","cited_by_count":90},{"id":"2101.06541","title":"SceneGen: Learning to Generate Realistic Traffic Scenes","created":"2021-01-16","cited_by_count":84},{"id":"1911.10715","title":"Multi-Agent Game Abstraction via Graph Attention Neural Network","created":"2019-11-25","cited_by_count":82},{"id":"2111.12083","title":"VISTA 2.0: An Open, Data-driven Simulator for Multimodal Sensing and Policy Learning for Autonomous Vehicles","created":"2021-11-23","cited_by_count":81},{"id":"2208.12403","title":"BITS: Bi-level Imitation for Traffic Simulation","created":"2022-08-26","cited_by_count":80},{"id":"2404.10595","title":"Automated Evaluation of Large Vision-Language Models on Self-driving Corner Cases","created":"2024-04-16","cited_by_count":77},{"id":"2303.17220","title":"Milestones in Autonomous Driving and Intelligent Vehicles: Survey of Surveys","created":"2023-03-30","cited_by_count":75},{"id":"2101.05436","title":"Learning Safe Multi-Agent Control with Decentralized Neural Barrier Certificates","created":"2021-01-14","cited_by_count":74},{"id":"1710.05465","title":"Flow: A Modular Learning Framework for Mixed Autonomy Traffic","created":"2017-10-16","cited_by_count":73},{"id":"1707.06600","title":"A multi-agent reinforcement learning model of common-pool resource appropriation","created":"2017-07-20","cited_by_count":69},{"id":"2405.11106","title":"LLM-based Multi-Agent Reinforcement Learning: Current and Future Directions","created":"2024-05-17","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":"2010.08184","title":"PRIMAL2: Pathfinding via Reinforcement and Imitation Multi-Agent Learning -- Lifelong","created":"2020-10-16","cited_by_count":63},{"id":"2101.11196","title":"Safe Multi-Agent Reinforcement Learning via Shielding","created":"2021-01-27","cited_by_count":61},{"id":"2306.12241","title":"ScenarioNet: Open-Source Platform for Large-Scale Traffic Scenario Simulation and Modeling","created":"2023-06-21","cited_by_count":60},{"id":"2305.01263","title":"How Simulation Helps Autonomous Driving:A Survey of Sim2real, Digital Twins, and Parallel Intelligence","created":"2023-05-02","cited_by_count":58},{"id":"2206.09889","title":"Nocturne: a scalable driving benchmark for bringing multi-agent learning one step closer to the real world","created":"2022-06-20","cited_by_count":56}],"next_cursor":"100"}