Q-Learning: Learning the Value of Every Action

The five-step Q-learning update loop, the update rule itself, and the exploration-versus-exploitation trade-off every practical RL agent has to balance with an epsilon-greedy policy.

~5 min total·4 quadrants of structured content

By the end of this topic, you will

List the five steps of the Q-learning update loop in order
Write the Q-learning update rule and explain the role of the learning rate and discount factor
Explain the exploration-versus-exploitation trade-off and what an epsilon-greedy policy does about it

Quadrant 1 · e-Tutorial

Video lectures and walkthroughs

Video content coming soon.

Quadrant 2 · e-Content

Articles and case studies

Q-Learning: Learning the Value of Every Action

Q-learning learns a table of the expected future reward of every state-action pair, nudging each estimate toward the reward just observed plus the best value achievable from here on.

Quadrant 3 · Web Resources