A collection of frequently asked questions in Reinforcement Learning.


Reinforcement learning is complex subject and innocuous sounding questions can have complicated answers. I present some of most frequently asked questions below.

Frequently Asked Questions

Phil Winder, Jan 2021

Learning RL How can I Learn RL? Do I Need To Know How to Program? I’m Finding it Hard RL Usage Is RL Better than ML? Examples of Using RL in Production Use Cases Replacing Teams of Data Scientists with RL How is Deploying RL Different to Deploying ML? Simplifying RL Problems RL for Auto-ML Simulations of Business Use Cases RL In Industry What use cases that are currently solved by ML, better solved by RL?

Presentation: Industrial Applications of Reinforcement Learning

Phil Winder, Nov 2020

Abstract Reinforcement learning (RL), a sub-discipline of machine learning, has been gaining academic and media notoriety after hyped marketing “reveals” of agents playing various games. But these hide the fact that RL is immensely useful in may practical, industrial situations where hand-coding strategies or policies would be impractical or sub-optimal. Following the theme of my new book (https://rl-book.com), I present a rebuttal to the hyperbole by analysing five different industrial case studies from a variety of sectors.

RL Book and Topic Recommendations

Aug 2020

Multi-Agent Reinforcement Learning I’d like to learn more about the interplay between Reinforcement Learning and Multi-Agent Systems. Can you suggest some study resources such as books and scientific articles from where I can start learning? Multi-agent reinforcement learning (MARL) is a hot topic. This is because in the future, multiple agents are more likely to be able to solve a problem faster and better than they could alone. But the problem is that it makes the problem highly non-stationary.