Wed, Jun 09 2021 to Fri, Jun 11 2021
Reinforcement learning (RL) addresses problems of sequential decision making and stochastic control and is strongly connected to dynamic programming and Markov decision processes. In the last decades, it has gained importance and has become a major field of study in machine learning and artificial intelligence. Researchers from a variety of scientific fields that reach from cognitive sciences, neurology and psychology to computer science, physics, and mathematics, have developed algorithms and techniques with impressive applications as well as mathematical foundations.
Reinforcement learning is based on the simple idea of learning by trial and error while interacting with an environment. At each step, the agent performs an action and receives a reward depending on the starting state, the action, and the environment. The agent learns to choose actions that maximize the sum of all rewards in the long run. The resulting choice of action for each state is called a policy. Finding optimal policies is the primary objective of reinforcement learning.
Date: June 9 - 11, 2021
Time: 11:15 am - 1:15 pm
To register please click here.
The sessions will be conducted over three days, with two hours a day of online lecture followed by 90 minutes of tutorials/interactive sessions, affixed with further take-home exercises.
Jonathan Shock (University of Cape Town)
Andreas Matt (Imaginary, Berlin)
RL - introduction and basics
History of reinforcement learning: psychology, dynamic programming
Markov Decision Processes
Value Functions, Action-Values, Policies
Grid world example with Value Iteration
RL - model free methods
Deep Q learning
Actor Critic Methods
Policy methods - the reinforce algorithm (click here)
ML and RL - applications, communication, and ethics
This would be more an applied, less mathematical, more 'playful' module.