Introduction of universe and Gym, frameworks by openAI
Provide overview for reinforcement learning and provide Jupyter Notebook to train a agent in game.
Give a walk though of using Tensorflow to train an agent interactive with the environment
Day 2 (5th November) 11:50 AM - 12:20 PM
AC1 Lecture Hall LT-16
English (English Slides)
Speaker
Holman Tai Holman Tai
Holman Tai is currently a researcher at Sensetime, a AI company startup provide computer vision products and solutions. He is passionate in reinforcement learning and deep learning.
Nationality: Hong Kong