Building Scalable Framework and Environment of Reinforcement Learning
Deep Reinforcement Learning (DRL) has made strong progress in many tasks that are traditionally considered to be difficult, such as complete information games, navigation, architecture search, etc. Although the basic principle of DRL is quite simple and straightforward, to make it work often requires substantially more samples with more computational resource, compared to traditional supervised training. This task presents our recent open-sourced works: efficient, lightweight and flexible frameworks and diverse 3D environments, to facilitate DRL research. We show the scalability of our platforms by reproducing and open sourcing AlphaGoZero/AlphaZero framework using 2000 GPUs, achieving super-human performance of Go AI. We also show usability of our platform by training agents in real-time strategy games and navigations, and show interesting behaviors using only a small amount of resource.
Yuandong Tian is a Research Scientist and Manager in Facebook AI Research, working on deep reinforcement learning and its applications in games, and theoretical analysis of deep models. Prior to that, he was a Software Engineer/Researcher in Google Self-driving Car team during 2013-2014. He received Ph.D in Robotics Institute, Carnegie Mellon University on 2013, Bachelor and Master degree of Computer Science in Shanghai Jiao Tong University. He is the recipient of 2013 ICCV Marr Prize Honorable Mentions.