{"list":"other","total":56,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942},{"id":"2301.00493","title":"Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting","created":"2023-01-02","cited_by_count":707},{"id":"1702.08165","title":"Reinforcement Learning with Deep Energy-Based Policies","created":"2017-02-27","cited_by_count":669},{"id":"2104.10133","title":"Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset","created":"2021-04-20","cited_by_count":537},{"id":"1705.05065","title":"AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles","created":"2017-05-15","cited_by_count":523},{"id":"1710.10044","title":"Distributional Reinforcement Learning with Quantile Regression","created":"2017-10-27","cited_by_count":474},{"id":"2308.01898","title":"UniSim: A Neural Closed-Loop Sensor Simulator","created":"2023-08-03","cited_by_count":297},{"id":"2109.12674","title":"MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning","created":"2021-09-26","cited_by_count":290},{"id":"2101.06557","title":"TrafficSim: Learning to Simulate Realistic Multi-Agent Behaviors","created":"2021-01-17","cited_by_count":193},{"id":"2109.11251","title":"Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning","created":"2021-09-23","cited_by_count":186},{"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":"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":"2112.05077","title":"Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Prior","created":"2021-12-09","cited_by_count":139},{"id":"2101.06549","title":"AdvSim: Generating Safety-Critical Scenarios for Self-Driving Vehicles","created":"2021-01-16","cited_by_count":137},{"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":"2006.12007","title":"Near-Optimal Reinforcement Learning with Self-Play","created":"2020-06-22","cited_by_count":109},{"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":"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":"2101.06541","title":"SceneGen: Learning to Generate Realistic Traffic Scenes","created":"2021-01-16","cited_by_count":84},{"id":"2208.12403","title":"BITS: Bi-level Imitation for Traffic Simulation","created":"2022-08-26","cited_by_count":80},{"id":"2105.12332","title":"SimNet: Learning Reactive Self-driving Simulations from Real-world Observations","created":"2021-05-26","cited_by_count":77},{"id":"2110.04184","title":"When Can We Learn General-Sum Markov Games with a Large Number of Players Sample-Efficiently?","created":"2021-10-08","cited_by_count":67},{"id":"2206.05825","title":"A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games","created":"2022-06-12","cited_by_count":66},{"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":"2408.01584","title":"GPUDrive: Data-driven, multi-agent driving simulation at 1 million FPS","created":"2024-08-02","cited_by_count":45},{"id":"2110.05682","title":"Provably Efficient Reinforcement Learning in Decentralized General-Sum Markov Games","created":"2021-10-12","cited_by_count":42},{"id":"1911.04074","title":"SUMMIT: A Simulator for Urban Driving in Massive Mixed Traffic","created":"2019-11-11","cited_by_count":40},{"id":"2102.11494","title":"Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games","created":"2021-02-23","cited_by_count":40},{"id":"2407.02797","title":"Solving Motion Planning Tasks with a Scalable Generative Model","created":"2024-07-03","cited_by_count":40},{"id":"2207.09081","title":"Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoning","created":"2022-07-19","cited_by_count":34},{"id":"2306.10508","title":"QCNeXt: A Next-Generation Framework For Joint Multi-Agent Trajectory Prediction","created":"2023-06-18","cited_by_count":31},{"id":"2404.02524","title":"Versatile Behavior Diffusion for Generalized Traffic Agent Simulation","created":"2024-04-03","cited_by_count":30},{"id":"2210.14413","title":"InterSim: Interactive Traffic Simulation via Explicit Relation Modeling","created":"2022-10-26","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":"2210.01050","title":"Faster Last-iterate Convergence of Policy Optimization in Zero-Sum Markov Games","created":"2022-10-03","cited_by_count":26},{"id":"2311.11056","title":"Choose Your Simulator Wisely: A Review on Open-source Simulators for Autonomous Driving","created":"2023-11-18","cited_by_count":26},{"id":"2107.13090","title":"Policy Gradient Methods Find the Nash Equilibrium in N-player General-sum Linear-quadratic Games","created":"2021-07-27","cited_by_count":25},{"id":"2311.01394","title":"Learning Realistic Traffic Agents in Closed-loop","created":"2023-11-02","cited_by_count":24},{"id":"2206.09495","title":"The Power of Regularization in Solving Extensive-Form Games","created":"2022-06-19","cited_by_count":21},{"id":"2408.00766","title":"Optimizing Diffusion Models for Joint Trajectory Prediction and Controllable Generation","created":"2024-08-01","cited_by_count":18},{"id":"2208.00094","title":"Robust Trajectory Prediction against Adversarial Attacks","created":"2022-07-29","cited_by_count":17},{"id":"2404.16147","title":"Chat2Scenario: Scenario Extraction From Dataset Through Utilization of Large Language Model","created":"2024-04-24","cited_by_count":14},{"id":"2405.09111","title":"CarDreamer: Open-Source Learning Platform for World Model based Autonomous Driving","created":"2024-05-15","cited_by_count":13},{"id":"2303.13830","title":"Editing Driver Character: Socially-Controllable Behavior Generation for Interactive Traffic Simulation","created":"2023-03-24","cited_by_count":10},{"id":"2212.01441","title":"Multi-Agent Reinforcement Learning with Reward Delays","created":"2022-12-02","cited_by_count":9},{"id":"2405.18209","title":"Safe Multi-Agent Reinforcement Learning with Bilevel Optimization in Autonomous Driving","created":"2024-05-28","cited_by_count":9},{"id":"2105.13407","title":"Manifold-constrained Gaussian process inference for time-varying parameters in dynamic systems","created":"2021-05-27","cited_by_count":8},{"id":"2405.04491","title":"TorchDriveEnv: A Reinforcement Learning Benchmark for Autonomous Driving with Reactive, Realistic, and Diverse Non-Playable Characters","created":"2024-05-07","cited_by_count":6},{"id":"2202.00081","title":"On solutions of the distributional Bellman equation","created":"2022-01-31","cited_by_count":2},{"id":"2405.11746","title":"Configurable Mirror Descent: Towards a Unification of Decision Making","created":"2024-05-20","cited_by_count":1}],"next_cursor":null}