Guardado en:
Detalles Bibliográficos
Autores principales: Wang, Ziyan, Chen, Peng, Li, Ding, Li, Chiwei, Zhang, Qichao, Xia, Zhongpu, Yu, Guizhen
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2603.24989
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908916031422464
author Wang, Ziyan
Chen, Peng
Li, Ding
Li, Chiwei
Zhang, Qichao
Xia, Zhongpu
Yu, Guizhen
author_facet Wang, Ziyan
Chen, Peng
Li, Ding
Li, Chiwei
Zhang, Qichao
Xia, Zhongpu
Yu, Guizhen
contents Learning diverse and high-fidelity traffic simulations from human driving demonstrations is crucial for autonomous driving evaluation. The recent next-token prediction (NTP) paradigm, widely adopted in large language models (LLMs), has been applied to traffic simulation and achieves iterative improvements via supervised fine-tuning (SFT). However, such methods limit active exploration of potentially valuable motion tokens, particularly in suboptimal regions. Entropy patterns provide a promising perspective for enabling exploration driven by motion token uncertainty. Motivated by this insight, we propose a novel tokenized traffic simulation policy, R1Sim, which represents an initial attempt to explore reinforcement learning based on motion token entropy patterns, and systematically analyzes the impact of different motion tokens on simulation outcomes. Specifically, we introduce an entropy-guided adaptive sampling mechanism that focuses on previously overlooked motion tokens with high uncertainty yet high potential. We further optimize motion behaviors using Group Relative Policy Optimization (GRPO), guided by a safety-aware reward design. Overall, these components enable a balanced exploration-exploitation trade-off through diverse high-uncertainty sampling and group-wise comparative estimation, resulting in realistic, safe, and diverse multi-agent behaviors. Extensive experiments on the Waymo Sim Agent benchmark demonstrate that R1Sim achieves competitive performance compared to state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2603_24989
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Learning Rollout from Sampling:An R1-Style Tokenized Traffic Simulation Model
Wang, Ziyan
Chen, Peng
Li, Ding
Li, Chiwei
Zhang, Qichao
Xia, Zhongpu
Yu, Guizhen
Robotics
Artificial Intelligence
Learning diverse and high-fidelity traffic simulations from human driving demonstrations is crucial for autonomous driving evaluation. The recent next-token prediction (NTP) paradigm, widely adopted in large language models (LLMs), has been applied to traffic simulation and achieves iterative improvements via supervised fine-tuning (SFT). However, such methods limit active exploration of potentially valuable motion tokens, particularly in suboptimal regions. Entropy patterns provide a promising perspective for enabling exploration driven by motion token uncertainty. Motivated by this insight, we propose a novel tokenized traffic simulation policy, R1Sim, which represents an initial attempt to explore reinforcement learning based on motion token entropy patterns, and systematically analyzes the impact of different motion tokens on simulation outcomes. Specifically, we introduce an entropy-guided adaptive sampling mechanism that focuses on previously overlooked motion tokens with high uncertainty yet high potential. We further optimize motion behaviors using Group Relative Policy Optimization (GRPO), guided by a safety-aware reward design. Overall, these components enable a balanced exploration-exploitation trade-off through diverse high-uncertainty sampling and group-wise comparative estimation, resulting in realistic, safe, and diverse multi-agent behaviors. Extensive experiments on the Waymo Sim Agent benchmark demonstrate that R1Sim achieves competitive performance compared to state-of-the-art methods.
title Learning Rollout from Sampling:An R1-Style Tokenized Traffic Simulation Model
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2603.24989