Skip to content
reinforcement learning

File:Reinforcement_learning_diagram.svg · Wikimedia Commons · See Wikimedia Commons

EntityQ830687· pop 43· linked from 834 articles

reinforcement learning

Sign in to save

Also known as RL

type of machine learning where an agent learns how to behave in an environment by performing actions and receiving rewards or penalties in return, aiming to maximize the cumulative reward over time

Research

89,335 papers

via PubMed

Wikidata facts

Show 4 more facts
ACM Classification Code (2012)
10010261
social media followers
30816
Commons category
Reinforcement learning
Sources (5)

via Wikidata · CC0

~40 min read

Article

The typical framing of a reinforcement learning (RL) scenario: an agent takes actions in an environment, which is interpreted into a reward and a state representation, which are fed back to the agent.

In machine learning and optimal control, reinforcement learning (RL) is concerned with how an intelligent agent should take actions in a dynamic environment in order to maximize a reward signal. Reinforcement learning is one of the three basic machine learning paradigms, alongside supervised learning and unsupervised learning.

Connections

Categories