Q-learning is a model-free reinforcement learning algorithm that trains an agent to assign values to its possible actions in each state, without needing a model of the environment's dynamics, by iteratively updating its estimates from the rewards and states it actually observes. It can handle environments with stochastic transitions and rewards. Chris Watkins introduced Q-learning in 1989, and a proof of its convergence was published by Watkins and Peter Dayan in 1992. This description is adapted from Wikipedia contributors under CC BY-SA 4.0; changes were made. https://creativecommons.org/licenses/by-sa/4.0/
Facts
Credited ToChris Watkins, 1989; convergence proof with Peter Dayan, 1992. 1 Connections
Associated With
Contrasted directly in the reinforcement-learning literature as the standard off-policy/on-policy temporal-difference control pair. Verified en.wikipedia.org/wiki/State-action-reward-state-action: "While SARSA learns the Q values associated with taking the policy it follows itself, Watkin's Q-learning learns the Q values associated with taking the optimal policy while following an exploration/exploitation policy."
In Field
Source Wikipedia: Q-Learning Algorithm
Sources
1. Wikipedia: Q-Learning Algorithm
Wikimedia FoundationLead section
Q-learning is a reinforcement learning algorithm that trains an agent to assign values to its possible actions based on its current state, without requiring a model of the environment (model-free).
History
Q-learning was introduced by Chris Watkins in 1989. A convergence proof was presented by Watkins and Peter Dayan in 1992, building on Watkins' doctoral dissertation, Learning from Delayed Rewards.
In Field: Machine Learning, Lead
Q-learning is a reinforcement learning algorithm that trains an agent to assign values to its possible actions based on its current state, without requiring a model of the environment (model-free).
In Group: Reinforcement Learning and Bandit Algorithms, Lead
Q-learning is a reinforcement learning algorithm that trains an agent to assign values to its possible actions based on its current state, without requiring a model of the environment (model-free).
View the Source 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.