Control systems and reinforcement learning sean meyn

In the standard model free setting, RL agents solve prediction tasks by learning an action value function Q(x,a), where x is the situation (“in bed”), and the action “a” could be “let the dog out”.
The control task involves finding the action that maximizes the action value function in any given state.
Reinforcement learning is a machine learning training method based on rewarding desired behaviors and punishing undesired ones.
In general, a reinforcement learning agent -- the entity being trained -- is able to perceive and interpret its environment, take actions and learn through trial and error.
Reinforcement learning systems can make decisions in one of two ways.
In the model-based approach, a system uses a predictive model of the world to ask questions of the form “what will happen if I do x?” to choose the best x ¹.

Book description This book is designed to explain the science behind reinforcement learning and optimal control in a way that is accessible to students with a background in calculus and matrix algebra.

Categories