Search Results for author: Quanyi Li

Found 11 papers, 6 papers with code

A Holistic Framework Towards Vision-based Traffic Signal Control with Microscopic Simulation

no code implementations11 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.

Benchmarking

GenNBV: Generalizable Next-Best-View Policy for Active 3D Reconstruction

no code implementations25 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.

3D Reconstruction Reinforcement Learning (RL)

Guarded Policy Optimization with Imperfect Online Demonstrations

no code implementations3 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.

Continuous Control Efficient Exploration +2

Human-AI Shared Control via Policy Dissection

1 code implementation31 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.

Autonomous Driving Reinforcement Learning (RL)

Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization

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.

Imitation Learning reinforcement-learning +1

Safe Driving via Expert Guided Policy Optimization

1 code implementation13 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.

Offline RL reinforcement-learning +1

MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning

2 code implementations26 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.

Benchmarking Decision Making +5

Improving the Generalization of End-to-End Driving through Procedural Generation

2 code implementations26 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.

Autonomous Driving

Cannot find the paper you are looking for? You can Submit a new open access paper.