Rayark Inc.

My main job is to design game AI for a real-time strategy game Soul of Eden.

More specifically speaking, I designed a deep reinforcement learning model based on Asynchronous Advantage Actor-Critic (A3C) algorithm without any supervised data. My model outperformed all of the rule-based models previously used by the company, with win rate more than 80%. I not only built the model but integrated the model (written in Python) into the real game (written in C#).

My first model (RNN model) proposal was demonstrated here (presented in National Taiwan University).
The sample code of my reinforcement learning model can be accessed here.


Formosa Grand Challenge

Formosa Grand Challenge

I helped organize Formosa Grand Challenge warm-up competition under Prof. Hung-Yi Lee’s leading.

Formosa Grand Challenge is the largest national AI competition in Taiwan, funded NT$100,000,000 (US$3,500,000) by the Taiwan government. We successfully attracted 100+ teams to participate in the warm-up competition.

My main job was to provide baseline for the competition and to design the questions for the competition. Specifically, I designed a seq2seq with attention model for the baseline, processed raw data collected from real world TV programs in Taiwan and then designed the questions.

See the news from Taiwan’s media udn.com, China Time and TechOrange.