Reinforcement Learning: an Easy Introduction to Value Iteration

Learn the fundamentals of RL and how to apply Value Iteration to a simple example problem

Value Iteration (VI) is typically one of the first algorithms introduced on the Reinforcement Learning (RL) learning pathway. The underlying specifics of the algorithm introduce some of the most fundamental aspects of RL and, hence, it is important to master VI before progressing to more complex RL algorithms. Yet, this can be tricky to get your head around.

This article is designed to be …

algorithm algorithms apply dynamic-programming easy example fundamentals introduction iteration learn machine learning reinforcement reinforcement learning robotics simple value value-iteration