Postdoctoral Researcher at City University of Hong Kong, working on DRL, Robotics, and manipulation. I also share my latest ideas on Xiaohongshu.
HIL-RL. The official repository for the paper "Real-world Reinforcement Learning from Suboptimal Interventions”.
58DRL-SIM. Code for paper Social-Aware Incentive Mechanism for Vehicular Crowdsensing by Deep Reinforcement Learning
24T2VLM. [ICCV'25] T2 -VLM: Training-Free Generation of Temporally Consistent Rewards from VLMs
16Qlearning. comparison Q-learning with Sarsa
12gMADRL-VCS. The official implementation of gMADRL-VCS
11DQN. using Deep Q Network to train CartPole
2lerobot. A fork of the LeRobot repository that includes online methods such as SiLRI, HG-Dagger, and HIL-SERL.
2MrCheck. 一款好用的记账app
1rl_envs. A real-world environment wrapper that supports human-in-the-loop RL for robotics.
1