- Home
- Insights
- The revenue lexicon
- Artificial intelligence
- Machine learning
- Reinforcement learning
Glossary
Reinforcement learning
Subject areaArtificial intelligence
Reinforcement learning is the form of machine learning in which an agent learns by trial and error, acting in an environment and receiving rewards or penalties.
Over time it finds the strategy that maximises the total reward. The idea comes from behavioural psychology; its computing form was systematised by Richard Sutton and Andrew Barto in the textbook Reinforcement Learning (1998). The best-known case is European: AlphaGo by DeepMind, a company founded in London, which in 2016 beat the champion Lee Sedol at the game of Go. The same method, with human judgement as the reward, is used today to make language models useful and safe.
An example
A system that chooses which offer to show each visitor and learns, from clicks and purchases, which one works best.
broader entriesthis entry and narrowertwo levels down← up · → down
Enrico Giubertoni. Licensed under CC BY-NC 4.0: you may quote, translate and adapt this entry with the author’s name and a link, stating any changes. For commercial use, write to info@enricogiubertoni.com
Spotted an inaccuracy or something that needs updating? Write to info@enricogiubertoni.com and help make this glossary a better place.
What are your business challenges?
Tell us about your priorities and the objectives you want to reach.
You will receive a free, targeted answer within one working day.