Machine Learning Researcher
91544.png
kisspng-google-scholar-education-researc
dblp-512.png
iconmonstr-linkedin-3.png

Gallery

Back in 2016, we were the first team to show that AI (BiCNet) could master human-level micro-management skills in playing StarCraft battles games.

Our team of Mean-Field Q-learners savage DQNs.

Multiagent techniques could efficiently dispatch Uber orders such that the supply demand gap in the CBD area can be significantly decreased throughout the whole day. 

Revenue-oriented order dispatch

Multi-agent powered order dispatch

We can use the multi-agent reinforcement learning techniques to mimic the spontaneous Mexican wave in the stadium.

Our multi-agent policy evaluation techniques can find the best combination of joint strategy profile for high-way driving, meanwhile finding Nash equilibrium on two-player game is known to be PPAD-complete (i.e. very hard).