Ben Duffy is a Computer Engineer/Data Scientist with experience in Computer Vision, Natural Language Processing and Reinforcement Learning, from both research and engineering standpoints. Together with the MTank team, he keeps up to date with the very frontier of research within these and related domains. By being fanatically obsessed with both the big picture view and specific details of how AI is progressing, he strives to impart this knowledge to the general public.
Reinforcement Learning (RL), the field of sequential decision making, has evolved significantly within the last few years, achieving super-human performance in solving complex board games (AlphaGo -> AlphaGoZero -> AlphaZero), 2D (Atari) and 3D games (Doom, Quake, StarCraft). But this is not just about games, this is about solving arbitrary problems with truly general algorithms. Fully dedicated to this pursuit, there is a huge research community involved with the ultimate goal of creating an "artificial general intelligence".
This talk will give an overview of the main breakthroughs, paradigms, formulations, and obstacles within RL to quickly get you up to speed with where the field currently is and where it is going.
Ben with the team at MTank created unique resources and reference material for anyone who wants to discover the changes happening at a lightning pace within AI.