no code implementations • 11 Mar 2024 • Pan He, Quanyi Li, Xiaoyong Yuan, Bolei Zhou
Traffic signal control (TSC) is crucial for reducing traffic congestion that leads to smoother traffic flow, reduced idling time, and mitigated CO2 emissions.
no code implementations • 25 Feb 2024 • Xiao Chen, Quanyi Li, Tai Wang, Tianfan Xue, Jiangmiao Pang
Previous works attempt to automate this process using the Next-Best-View (NBV) policy for active 3D reconstruction.
1 code implementation • 18 Dec 2023 • Junfeng Long, ZiRui Wang, Quanyi Li, Jiawei Gao, Liu Cao, Jiangmiao Pang
Robust locomotion control depends on accurate state estimations.
no code implementations • 19 Oct 2023 • Linrui Zhang, Zhenghao Peng, Quanyi Li, Bolei Zhou
Driving safety is a top priority for autonomous vehicles.
no code implementations • 3 Mar 2023 • Zhenghai Xue, Zhenghao Peng, Quanyi Li, Zhihan Liu, Bolei Zhou
Assuming optimal, the teacher policy has the perfect timing and capability to intervene in the learning process of the student agent, providing safety guarantee and exploration guidance.
1 code implementation • 31 May 2022 • Quanyi Li, Zhenghao Peng, Haibin Wu, Lan Feng, Bolei Zhou
Inspired by the neuroscience approach to investigate the motor cortex in primates, we develop a simple yet effective frequency-based approach called \textit{Policy Dissection} to align the intermediate representation of the learned neural controller with the kinematic attributes of the agent behavior.
no code implementations • ICLR 2022 • Quanyi Li, Zhenghao Peng, Bolei Zhou
HACO can train agents to drive in unseen traffic scenarios with a handful of human intervention budget and achieve high safety and generalizability, outperforming both reinforcement learning and imitation learning baselines with a large margin.
2 code implementations • NeurIPS 2021 • Zhenghao Peng, Quanyi Li, Ka Ming Hui, Chunxiao Liu, Bolei Zhou
Self-Driven Particles (SDP) describe a category of multi-agent systems common in everyday life, such as flocking birds and traffic flows.
Multi-agent Reinforcement Learning reinforcement-learning +1
1 code implementation • 13 Oct 2021 • Zhenghao Peng, Quanyi Li, Chunxiao Liu, Bolei Zhou
Offline RL technique is further used to learn from the partial demonstration generated by the expert.
2 code implementations • 26 Sep 2021 • Quanyi Li, Zhenghao Peng, Lan Feng, Qihang Zhang, Zhenghai Xue, Bolei Zhou
Based on MetaDrive, we construct a variety of RL tasks and baselines in both single-agent and multi-agent settings, including benchmarking generalizability across unseen scenes, safe exploration, and learning multi-agent traffic.
2 code implementations • 26 Dec 2020 • Quanyi Li, Zhenghao Peng, Qihang Zhang, Chunxiao Liu, Bolei Zhou
We validate that training with the increasing number of procedurally generated scenes significantly improves the generalization of the agent across scenarios of different traffic densities and road networks.