Why Discount Future Rewards In Reinforcement Learning?

A discussion on discount rates from the perspectives of mathematics, finance, life, and of course Reinforcement Learning.

Not that kind of discount. Photo by Artem Beliaikin on Unsplash

Although discount rates are an integral part of Markov decision problems and Reinforcement Learning (RL), we often select γ=0.9 or γ=0.99 without thinking twice. Surely…