Google recently released a research framework for fast prototyping of reinforcement learning algorithms called “Dopamine”. They say that it aims to fill the need for a small, easily grokked codebase in which users can freely experiment with wild ideas (speculative research). In this live stream i’ll test it out, try out a few basic reinforcement learning algorithms and compare it to similar frameworks. You can code along with me using CoLab. Get hype!
Published on September 12, 2018 by Carlo LepelaarsCategory AI Course Tag A.I. (Artificial Intelligence) Course Full Course Google Google Dopamine Move 37 Reinforcement Learning Siraj Raval The School of AI
June 18, 20181,3604 0
(18 min.) Siraj Raval (Decentralized Applications): How Do We Prevent an AI Apocalypse? | TNW Conference 2017
February 18, 20182564 1
August 13, 20181342 0