Muhammad Ali Chaudhry is a PostGraduate Researcher at University College London (UCL). In this talk he will share the choices that one has to make in modelling a Reinforcement Learning algorithm. He will discuss different types of Reinforcement Learning agents like Model-free, Model-based, Value-based, Policy-based and Actor-Critic. He will also discuss the trade-off between Exploration vs Exploitation and Planning vs Control using Temporal Difference Learning, Dynamic Programming and Monte Carlo approaches.
YOU MAY ALSO LIKE:
Reinforcement Learning Basics: Modelling your Algorithms
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.