Zhenghao Peng

Human-in-the-loop Policy Learning PVP Video (NeurIPS 2023 Spotlight)

Human-in-the-loop Policy Learning PVP Video (NeurIPS 2023 Spotlight)
CAT: Closed-loop Adversarial Training for Safe End-to-End Driving (CoRL 2023)

CAT: Closed-loop Adversarial Training for Safe End-to-End Driving (CoRL 2023)
MetaDrive is SO FAST! Try out this Reinforcement Learning environment!

MetaDrive is SO FAST! Try out this Reinforcement Learning environment!
【原神】2023年1月8日墨西哥城原神线下活动实拍 Genshin Impact Party in Mexico City CDMX, Jan 8, 2023

【原神】2023年1月8日墨西哥城原神线下活动实拍 Genshin Impact Party in Mexico City CDMX, Jan 8, 2023
Human-AI Shared Control via Policy Dissection (NeurIPS 2022)

Human-AI Shared Control via Policy Dissection (NeurIPS 2022)
【1080P高清重制】黑炮事件 The Black Cannon Incident 1985 国语中字 黄建新 刘子枫 国产老电影

【1080P高清重制】黑炮事件 The Black Cannon Incident 1985 国语中字 黄建新 刘子枫 国产老电影
【4K高清重制】错位 Dislocation 1986 国语中字 黄建新 刘子枫 国产老电影

【4K高清重制】错位 Dislocation 1986 国语中字 黄建新 刘子枫 国产老电影
MetaDrive: A lightweight and efficient driving simulator for reinforcement learning

MetaDrive: A lightweight and efficient driving simulator for reinforcement learning
How to learn a population of skilled drivers? Talk on Coordinated Policy Optimization (NeurIPS 2021)

How to learn a population of skilled drivers? Talk on Coordinated Policy Optimization (NeurIPS 2021)
Safe Driving via Expert Guided Policy Optimization Demo Video

Safe Driving via Expert Guided Policy Optimization Demo Video