Join this months London Reinforcement Learning for talks about the implementation of Deepmind's paper on Reinforcement Learning for Atari Games! Don't miss it!
In this talk Skif will discuss his implementation of Deepmind's paper on Reinforcement Learning for Atari Games published by Nature. It is considered a landmark paper in Reinforcement Learning literature in which an RL agent received human level performance a number of Atari games.
I work as a financial quantitative analyst; I have a background in statistics and economics. I am self-studying theoretical and practical aspects of reinforcement learning with the view of studying the subject at university at a post-graduate level. My day job involves a lot of programming (Python), as well as pushing for adoption of deep learning as a tool for financial analysis.
Monte Carlo Tree Search has proven to be one of the most productive techniques in Reinforcement Learning. It has produced state of the results in problems with humongous state spaces like Chess and Go. Ali will present the theory behind this Monte Carlo Tress Search and share its use cases.
Ali is a self-taught programmer, currently doing a PhD in Artificial Intelligence and Education at University College London. His research focuses on applying human-centered learning science theories on Deep Reinforcement Learning algorithms. These days he's obsessed with GANs and Variational Autoencoders.