English
Related papers

Related papers: RIFT: Group-Relative RL Fine-Tuning for Realistic …

200 papers

Supervised open-loop training has been widely adopted for training traffic simulation models; however, it fails to capture the inherently dynamic, multi-agent interactions common in complex driving scenarios. We introduce RLFTSim, a…

As the foundation of closed-loop training and evaluation in autonomous driving, traffic simulation still faces two fundamental challenges: covariate shift introduced by open-loop imitation learning and limited capacity to reflect the…

Robotics · Computer Science 2026-02-03 Keyu Chen , Wenchao Sun , Hao Cheng , Zheng Fu , Sifa Zheng

Realistic traffic simulation is crucial for developing self-driving software in a safe and scalable manner prior to real-world deployment. Typically, imitation learning (IL) is used to learn human-like traffic agents directly from…

Robotics · Computer Science 2023-11-03 Chris Zhang , James Tu , Lunjun Zhang , Kelvin Wong , Simon Suo , Raquel Urtasun

End-to-end autonomous driving is typically built upon imitation learning (IL), yet its performance is constrained by the quality of human demonstrations. To overcome this limitation, recent methods incorporate reinforcement learning (RL)…

Robotics · Computer Science 2026-04-13 Zhexi Lian , Haoran Wang , Xuerun Yan , Weimeng Lin , Xianhong Zhang , Yongyu Chen , Jia Hu

High-quality traffic flow generation is the core module in building simulators for autonomous driving. However, the majority of available simulators are incapable of replicating traffic patterns that accurately reflect the various features…

Open-loop imitation learning has advanced modern autonomous driving policy architectures, but closed-loop deployment remains vulnerable to policy-induced distribution shift. Existing post-training paradigms exhibit fundamental trade-offs:…

Machine Learning · Computer Science 2026-05-07 Keyu Chen , Nanfei Ye , Yida Wang , Wenchao Sun , Danqi Zhao , Hao Cheng , Sifa Zheng

Deep reinforcement learning policies achieve strong performance in complex continuous control environments with nonlinear contact forces. However, these policies often produce chaotic state dynamics, with trivially small changes to the…

Machine Learning · Computer Science 2026-04-28 Rory Young , Nicolas Pugeault

Modern approaches to autonomous driving rely heavily on learned components trained with large amounts of human driving data via imitation learning. However, these methods require large amounts of expensive data collection and even then face…

Scalable and realistic simulation of multi-agent traffic behavior is critical for advancing autonomous driving technologies. Although existing data-driven simulators have made significant strides in this domain, they predominantly rely on…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Muleilan Pei , Shaoshuai Shi , Shaojie Shen

Simulation offers a scalable and low-cost way to enrich vision-language-action (VLA) training, reducing reliance on expensive real-robot demonstrations. However, most sim-real co-training methods rely on supervised fine-tuning (SFT), which…

Robotics · Computer Science 2026-03-09 Liangzhi Shi , Shuaihang Chen , Feng Gao , Yinuo Chen , Kang Chen , Tonghe Zhang , Hongzhi Zang , Weinan Zhang , Chao Yu , Yu Wang

Existing evaluation paradigms for Autonomous Vehicles (AVs) face critical limitations. Real-world evaluation is often challenging due to safety concerns and a lack of reproducibility, whereas closed-loop simulation can face insufficient…

Reinforcement learning (RL) faces challenges in trajectory planning for urban automated driving due to the poor convergence of RL and the difficulty in designing reward functions. Consequently, few RL-based trajectory planning methods can…

Robotics · Computer Science 2025-07-17 Di Zeng , Ling Zheng , Xiantong Yang , Yinong Li

Optimizing accelerator control is a critical challenge in experimental particle physics, requiring significant manual effort and resource expenditure. Traditional tuning methods are often time-consuming and reliant on expert input,…

Accelerator Physics · Physics 2026-01-27 Anwar Ibrahim , Denis Derkach , Alexey Petrenko , Fedor Ratnikov , Maxim Kaledin

Reinforcement learning (RL) is a promising solution for autonomous vehicles to deal with complex and uncertain traffic environments. The RL training process is however expensive, unsafe, and time consuming. Algorithms are often developed…

Robotics · Computer Science 2022-11-29 Kevin Voogd , Jean Pierre Allamaa , Javier Alonso-Mora , Tong Duy Son

Traffic simulation aims to learn a policy for traffic agents that, when unrolled in closed-loop, faithfully recovers the joint distribution of trajectories observed in the real world. Inspired by large language models, tokenized multi-agent…

Machine Learning · Computer Science 2025-03-17 Zhejun Zhang , Peter Karkus , Maximilian Igl , Wenhao Ding , Yuxiao Chen , Boris Ivanovic , Marco Pavone

End-to-end models for autonomous driving hold the promise of learning complex behaviors directly from sensor data, but face critical challenges in safety and handling long-tail events. Reinforcement Learning (RL) offers a promising path to…

Computer Vision and Pattern Recognition · Computer Science 2026-03-12 Tianyi Yan , Tao Tang , Xingtai Gui , Yongkang Li , Jiasen Zhesng , Weiyao Huang , Lingdong Kong , Wencheng Han , Xia Zhou , Xueyang Zhang , Yifei Zhan , Kun Zhan , Cheng-zhong Xu , Jianbing Shen

While Supervised Fine-Tuning (SFT) and Rejection Sampling Fine-Tuning (RFT) are standard for LLM alignment, they either rely on costly expert data or discard valuable negative samples, leading to data inefficiency. To address this, we…

Machine Learning · Computer Science 2026-04-24 Zehua Liu , Shuqi Liu , Tao Zhong , Mingxuan Yuan

Reinforcement learning (RL) has shown promise in robotics, but deploying RL on real vehicles remains challenging due to the complexity of vehicle dynamics and the mismatch between simulation and reality. Factors such as tire…

Robotics · Computer Science 2025-11-11 Thomas Steinecker , Alexander Bienemann , Denis Trescher , Thorsten Luettel , Mirko Maehlisch

This paper presents CLIP-RLDrive, a new reinforcement learning (RL)-based framework for improving the decision-making of autonomous vehicles (AVs) in complex urban driving scenarios, particularly in unsignalized intersections. To achieve…

Robotics · Computer Science 2024-12-24 Erfan Doroudian , Hamid Taghavifar

Existing end-to-end autonomous driving (AD) algorithms typically follow the Imitation Learning (IL) paradigm, which faces challenges such as causal confusion and an open-loop gap. In this work, we propose RAD, a 3DGS-based closed-loop…

Computer Vision and Pattern Recognition · Computer Science 2025-10-22 Hao Gao , Shaoyu Chen , Bo Jiang , Bencheng Liao , Yiang Shi , Xiaoyang Guo , Yuechuan Pu , Haoran Yin , Xiangyu Li , Xinbang Zhang , Ying Zhang , Wenyu Liu , Qian Zhang , Xinggang Wang
‹ Prev 1 2 3 10 Next ›