Enhanced POET: Open-Ended Reinforcement Learning

This video will explain details behind the new Enhanced POET algorithm from Uber AI Labs! This is a really exciting algorithm for the co-evolution of agents and the environments they learn in! Extensions in this paper make the framework applicable to more general Machine Learning problems after being originally proven on Bipedal Walking agents. A very interesting finding from this study is that agents cannot be optimized from scratch to solve the complex environments that arise out of this co-evolution! Thanks for watching! Please Subscribe! Paper Links: Enhanced POET: https://ift.tt/2J4X81K Original POET: https://ift.tt/2xUnFwp Generative Teaching Networks: https://ift.tt/2w8Yd64 Learning to Continually Learn: https://ift.tt/2VG7dKi Thanks for watching! Please Subscribe!