A reinforcement learning method that updates value guesses step by step.
It is like fixing your pancake recipe after each pancake. Too pale? Turn up the heat before breakfast is over.
TD Learning updates an agent’s value guesses while it acts. It helps the agent learn as it goes.
RL
TD Learning is a classic RL method for updating value guesses step by step.
Q-Learning
Q-Learning uses TD Learning to update Q values before the whole run ends.
Actor-Critic
Actor-Critic often uses TD Learning to keep its critic improving.
Policy Gradient
TD Learning learns value guesses. Policy Gradient changes the policy more directly.