中文
相关论文

相关论文: Traffic expertise meets residual RL: Knowledge-inf…

200 篇论文

In the past decades, we have witnessed significant progress in the domain of autonomous driving. Advanced techniques based on optimization and reinforcement learning (RL) become increasingly powerful at solving the forward problem: given…

机器人学 · 计算机科学 2020-06-25 Zheng Wu , Liting Sun , Wei Zhan , Chenyu Yang , Masayoshi Tomizuka

Model-based reinforcement learning (RL) methods are appealing in the offline setting because they allow an agent to reason about the consequences of actions without interacting with the environment. Prior methods learn a 1-step dynamics…

机器学习 · 计算机科学 2022-11-07 Bogdan Mazoure , Benjamin Eysenbach , Ofir Nachum , Jonathan Tompson

Reinforcement learning (RL) is widely used in autonomous driving tasks and training RL models typically involves in a multi-step process: pre-training RL models on simulators, uploading the pre-trained model to real-life robots, and…

机器学习 · 计算机科学 2019-10-15 Xinle Liang , Yang Liu , Tianjian Chen , Ming Liu , Qiang Yang

Reinforcement learning (RL) has been a promising essence in future 5G-beyond and 6G systems. Its main advantage lies in its robust model-free decision-making in complex and large-dimension wireless environments. However, most existing RL…

机器人学 · 计算机科学 2025-02-04 Eslam Eldeeb , Hirley Alves

Applying reinforcement learning (RL) to real-world applications requires addressing a trade-off between asymptotic performance, sample efficiency, and inference time. In this work, we demonstrate how to address this triple challenge by…

机器学习 · 计算机科学 2024-07-03 Zakariae El Asri , Olivier Sigaud , Nicolas Thome

Model-based reinforcement learning (RL) is more sample efficient than model-free RL by using imaginary trajectories generated by the learned dynamics model. When the model is inaccurate or biased, imaginary trajectories may be deleterious…

机器学习 · 计算机科学 2021-04-12 Wenzhen Huang , Qiyue Yin , Junge Zhang , Kaiqi Huang

Safe and efficient autonomous driving maneuvers in an interactive and complex environment can be considerably challenging due to the unpredictable actions of other surrounding agents that may be cooperative or adversarial in their…

机器人学 · 计算机科学 2019-01-28 Pin Wang , Ching-Yao Chan , Hanhan Li

Offline reinforcement learning (RL) enables learning control policies by utilizing only prior experience, without any online interaction. This can allow robots to acquire generalizable skills from large and diverse datasets, without any…

机器学习 · 计算机科学 2021-09-24 Aviral Kumar , Anikait Singh , Stephen Tian , Chelsea Finn , Sergey Levine

In this paper, we propose Sparse Imitation Reinforcement Learning (SIRL), a hybrid end-to-end control policy that combines the sparse expert driving knowledge with reinforcement learning (RL) policy for autonomous driving (AD) task in CARLA…

计算机视觉与模式识别 · 计算机科学 2022-05-25 Yuci Han , Alper Yilmaz

Reinforcement Learning (RL) in Traffic Signal Control (TSC) faces significant hurdles in real-world deployment due to limited generalization to dynamic traffic flow variations. Existing approaches often overfit static patterns and use…

Urban Traffic Control (UTC) plays an essential role in Intelligent Transportation System (ITS) but remains difficult. Since model-based UTC methods may not accurately describe the complex nature of traffic dynamics in all situations,…

人工智能 · 计算机科学 2018-08-27 Yilun Lin , Xingyuan Dai , Li Li , Fei-Yue Wang

Traffic signal control is of critical importance for the effective use of transportation infrastructures. The rapid increase of vehicle traffic and changes in traffic patterns make traffic signal control more and more challenging.…

机器学习 · 计算机科学 2021-12-08 Xingshuai Huang , Di Wu , Michael Jenkin , Benoit Boulet

Residual Reinforcement Learning (RL) is a popular approach for adapting pretrained policies by learning a lightweight residual policy that provides corrective actions. While Residual RL is more sample-efficient than finetuning the entire…

Reinforcement learning (RL) constitutes a promising solution for alleviating the problem of traffic congestion. In particular, deep RL algorithms have been shown to produce adaptive traffic signal controllers that outperform conventional…

机器学习 · 统计学 2019-07-23 Filipe Rodrigues , Carlos Lima Azevedo

Reinforcement learning (RL) algorithms find applications in inventory control, recommender systems, vehicular traffic management, cloud computing and robotics. The real-world complications of many tasks arising in these domains makes them…

机器学习 · 计算机科学 2021-06-03 Sindhu Padakandla

Autonomous urban driving navigation with complex multi-agent dynamics is under-explored due to the difficulty of learning an optimal driving policy. The traditional modular pipeline heavily relies on hand-designed rules and the…

计算机视觉与模式识别 · 计算机科学 2018-07-11 Xiaodan Liang , Tairui Wang , Luona Yang , Eric Xing

Poor sample efficiency continues to be the primary challenge for deployment of deep Reinforcement Learning (RL) algorithms for real-world applications, and in particular for visuo-motor control. Model-based RL has the potential to be highly…

机器学习 · 计算机科学 2022-12-13 Nicklas Hansen , Yixin Lin , Hao Su , Xiaolong Wang , Vikash Kumar , Aravind Rajeswaran

Connected and Automated Hybrid Electric Vehicles have the potential to reduce fuel consumption and travel time in real-world driving conditions. The eco-driving problem seeks to design optimal speed and power usage profiles based upon…

机器学习 · 计算机科学 2022-02-01 Zhaoxuan Zhu , Nicola Pivaro , Shobhit Gupta , Abhishek Gupta , Marcello Canova

We present an online model-based reinforcement learning algorithm suitable for controlling complex robotic systems directly in the real world. Unlike prevailing sim-to-real pipelines that rely on extensive offline simulation and model-free…

机器人学 · 计算机科学 2026-05-07 Fang Nan , Hao Ma , Qinghua Guan , Josie Hughes , Michael Muehlebach , Marco Hutter

Emerging vehicular systems with increasing proportions of automated components present opportunities for optimal control to mitigate congestion and increase efficiency. There has been a recent interest in applying deep reinforcement…

人工智能 · 计算机科学 2022-08-02 Zhongxia Yan , Abdul Rahman Kreidieh , Eugene Vinitsky , Alexandre M. Bayen , Cathy Wu