A machine-learning paradigm in which an agent learns to act by trial and error within an environment, receiving rewards or penalties for its actions and adjusting its behavior over time to maximize its cumulative reward.
Facts
Core PrincipleAn intelligent agent learns how to take actions in a dynamic environment in order to maximize a reward signal. 1 Connections
In Field
Invented
Andrew Barto co-authored the standard textbook Reinforcement Learning: An Introduction with Richard Sutton, the field's defining synthesis.
Richard S. Sutton co-authored the standard textbook Reinforcement Learning: An Introduction with Andrew Barto, the field's defining synthesis.
Sources
1. Reinforcement learning, Wikipedia
Lead section, first sentenceQuote, Lead section, first sentence
is concerned with how an intelligent agent should take actions in a dynamic environment in order to maximize a reward signal
Reader Challenges (0)
No disputes yet. Spotted an error or a better source? Open the first one.
Sign in to dispute this or suggest a correction.