Q-Learning
A reinforcement learning algorithm that learns the value of actions in states to determine optimal behavior.
In-depth explanation
Q-learning learns a Q-function that estimates the expected future reward for taking an action in a state. It's model-free (doesn't need environment model) and off-policy (can learn from any experience). Deep Q-Networks (DQN) combine Q-learning with neural networks to handle large state spaces, achieving human-level performance on Atari games.
Examples
Related terms
More in Reinforcement Learning
Policy Gradient
Policy Gradient methods are a class of algorithms in reinforcement learning that optimize the policy directly by using the gradient of the expected reward with respect to the policy parameters.
Reinforcement Learning
Machine learning where an agent learns to make decisions by taking actions and receiving rewards or penalties.
Master Q-Learning.
Learn how to apply this concept with hands-on projects in our comprehensive AI programs.