• I’m pursuing my Computer Science PhD in University of Manchester, supervised by Dr. Ke Chen. Previously, I obtained my Master degree from UCL under the supervison of Prof. Jun Wang in 2018. I received my Bachelor’s Degree from Shanghai Jiao Tong University, where my undergraduate supervisors are Prof. Yong Yu and Prof. Weinan Zhang.

• My research mainly focuses on representation learning for control now. I am interested in how to make use of reinforcement learning to learn adaptive learning methods to different domains, make consciousness modeling and robotic control .

Recent Activities

• September 2020. Started my PhD in University of Manchester.
• Novemver, 2019. One paper accepted by AAAI 2020.
• September, 2019. One paper MVRL accepted by NeurIPS 2019.
• November, 2018. Joined Wayve to work on robotics and imitation learning in Cambridge.
• April, 2018. I build one bridge reinforcement learning environment based on Double Dummy Solver designed for bidding task in bridge game.
• March, 2018. Intergrate rllab hierarchical reinforcement learning gather and maze into openai gym environment.
• January, 2018. Find a bug in openai baseline TRPO implementation.
• September, 2017. Rewrite the StarCraft I API of Alibaba using TorchCraft v 1.3.0 and extend the environment to include more features. An implementation of BiCNet on StarCraft I is available in RL-forest.
• May, 2017. Implement the paper and achieve average 2500 on Atari Game Montezuma Revenge.