{"list":"other","total":64,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2503.14476","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","created":"2025-03-18","cited_by_count":2810},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"2212.10156","title":"Planning-oriented Autonomous Driving","created":"2022-12-20","cited_by_count":1087},{"id":"2303.12077","title":"VAD: Vectorized Scene Representation for Efficient Autonomous Driving","created":"2023-03-21","cited_by_count":622},{"id":"2106.11810","title":"NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles","created":"2021-06-22","cited_by_count":493},{"id":"2406.15349","title":"NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking","created":"2024-06-21","cited_by_count":354},{"id":"2406.03877","title":"Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving","created":"2024-06-06","cited_by_count":252},{"id":"2306.07962","title":"Parting with Misconceptions about Learning-based Vehicle Motion Planning","created":"2023-06-13","cited_by_count":242},{"id":"2405.19620","title":"SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representation","created":"2024-05-30","cited_by_count":241},{"id":"2306.03083","title":"MotionDiffuser: Controllable Multi-Agent Motion Prediction using Diffusion","created":"2023-06-05","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":"2210.17366","title":"Guided Conditional Diffusion for Controllable Traffic Simulation","created":"2022-10-31","cited_by_count":190},{"id":"2106.08417","title":"Scene Transformer: A unified architecture for predicting multiple agent trajectories","created":"2021-06-15","cited_by_count":165},{"id":"1912.09729","title":"Mastering Complex Control in MOBA Games with Deep Reinforcement Learning","created":"2019-12-20","cited_by_count":161},{"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":"2309.16534","title":"MotionLM: Multi-Agent Motion Forecasting as Language Modeling","created":"2023-09-28","cited_by_count":156},{"id":"2303.05760","title":"GameFormer: Game-theoretic Modeling and Learning of Transformer-based Interactive Prediction and Planning for Autonomous Driving","created":"2023-03-10","cited_by_count":141},{"id":"2501.15564","title":"Diffusion-Based Planning for Autonomous Driving with Flexible Guidance","created":"2025-01-26","cited_by_count":141},{"id":"2112.05077","title":"Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Prior","created":"2021-12-09","cited_by_count":139},{"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":"2306.06344","title":"Language-Guided Traffic Simulation via Scene-Level Diffusion","created":"2023-06-10","cited_by_count":111},{"id":"2210.06609","title":"TrafficGen: Learning to Generate Diverse and Realistic Traffic Scenarios","created":"2022-10-12","cited_by_count":106},{"id":"2202.02215","title":"A Survey on Safety-Critical Driving Scenario Generation -- A Methodological Perspective","created":"2022-02-04","cited_by_count":105},{"id":"2210.14222","title":"PlanT: Explainable Planning Transformers via Object-Level Representations","created":"2022-10-25","cited_by_count":105},{"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":"2405.14062","title":"ChatScene: Knowledge-Enabled Safety-Critical Scenario Generation for Autonomous Vehicles","created":"2024-05-22","cited_by_count":93},{"id":"2307.07947","title":"Language Conditioned Traffic Generation","created":"2023-07-16","cited_by_count":87},{"id":"2305.12032","title":"The Waymo Open Sim Agents Challenge","created":"2023-05-19","cited_by_count":86},{"id":"2101.06541","title":"SceneGen: Learning to Generate Realistic Traffic Scenes","created":"2021-01-16","cited_by_count":84},{"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":"2208.12403","title":"BITS: Bi-level Imitation for Traffic Simulation","created":"2022-08-26","cited_by_count":80},{"id":"2502.03349","title":"Robust Autonomy Emerges from Self-Play","created":"2025-02-05","cited_by_count":67},{"id":"2206.09682","title":"SafeBench: A Benchmarking Platform for Safety Evaluation of Autonomous Vehicles","created":"2022-06-20","cited_by_count":66},{"id":"2207.02749","title":"\"Curse of rarity\" for autonomous vehicles","created":"2022-07-06","cited_by_count":63},{"id":"2312.04535","title":"Trajeglish: Traffic Modeling as Next-Token Prediction","created":"2023-12-07","cited_by_count":60},{"id":"2303.04116","title":"TrafficBots: Towards World Models for Autonomous Driving Simulation and Motion Prediction","created":"2023-03-07","cited_by_count":56},{"id":"2009.08311","title":"Multimodal Safety-Critical Scenarios Generation for Decision-Making Algorithms Evaluation","created":"2020-09-16","cited_by_count":55},{"id":"2310.12432","title":"CAT: Closed-loop Adversarial Training for Safe End-to-End Driving","created":"2023-10-19","cited_by_count":54},{"id":"2412.12129","title":"SceneDiffuser: Efficient and Controllable Driving Simulation Initialization and Rollout","created":"2024-12-05","cited_by_count":48},{"id":"2312.13303","title":"RealGen: Retrieval Augmented Generation for Controllable Traffic Scenarios","created":"2023-12-19","cited_by_count":46},{"id":"2407.02797","title":"Solving Motion Planning Tasks with a Scalable Generative Model","created":"2024-07-03","cited_by_count":40},{"id":"2412.05334","title":"Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models","created":"2024-12-05","cited_by_count":40},{"id":"2303.16574","title":"FEND: A Future Enhanced Distribution-Aware Contrastive Learning Framework for Long-tail Trajectory Prediction","created":"2023-03-29","cited_by_count":31},{"id":"2310.15975","title":"Data-driven Traffic Simulation: A Comprehensive Review","created":"2023-10-24","cited_by_count":29},{"id":"2210.14413","title":"InterSim: Interactive Traffic Simulation via Explicit Relation Modeling","created":"2022-10-26","cited_by_count":27},{"id":"2403.17933","title":"SLEDGE: Synthesizing Driving Environments with Generative Models and Rule-Based Traffic","created":"2024-03-26","cited_by_count":27},{"id":"2403.19918","title":"CtRL-Sim: Reactive and Controllable Driving Agents with Offline Reinforcement Learning","created":"2024-03-29","cited_by_count":27},{"id":"2409.18343","title":"Improving Agent Behaviors with RL Fine-tuning for Autonomous Driving","created":"2024-09-26","cited_by_count":27},{"id":"2311.01394","title":"Learning Realistic Traffic Agents in Closed-loop","created":"2023-11-02","cited_by_count":24},{"id":"2412.17920","title":"Causal Composition Diffusion Model for Closed-loop Traffic Generation","created":"2024-12-23","cited_by_count":22},{"id":"2309.00709","title":"Reinforcement Learning with Human Feedback for Realistic Traffic Simulation","created":"2023-09-01","cited_by_count":21},{"id":"2409.05863","title":"Promptable Closed-loop Traffic Simulation","created":"2024-09-09","cited_by_count":20},{"id":"2207.08664","title":"Action-based Contrastive Learning for Trajectory Prediction","created":"2022-07-18","cited_by_count":15},{"id":"2406.02983","title":"FREA: Feasibility-Guided Generation of Safety-Critical Scenarios with Reasonable Adversariality","created":"2024-06-05","cited_by_count":13},{"id":"2504.10485","title":"Decoupled Diffusion Sparks Adaptive Scene Generation","created":"2025-04-14","cited_by_count":12},{"id":"2405.03807","title":"UniGen: Unified Modeling of Initial Agent States and Trajectories for Generating Autonomous Driving Scenarios","created":"2024-05-06","cited_by_count":10},{"id":"2012.11329","title":"CARLA Real Traffic Scenarios -- novel training ground and benchmark for autonomous driving","created":"2020-12-16","cited_by_count":8},{"id":"2110.14221","title":"Learning Diverse Policies in MOBA Games via Macro-Goals","created":"2021-10-27","cited_by_count":7},{"id":"2209.15133","title":"Modeling driver's evasive behavior during safety-critical lane changes:Two-dimensional time-to-collision and deep reinforcement learning","created":"2022-09-29","cited_by_count":7},{"id":"2503.05180","title":"Safety-Critical Traffic Simulation with Adversarial Transfer of Driving Intentions","created":"2025-03-07","cited_by_count":4}],"next_cursor":null}