Value Functions
Machine Learning · Further Education · Reinforcement Learning
This unit introduces the concept of value functions, which are functions that estimate the value of a state or action. Value functions are essential for value-based reinforcement learning algorithms, which learn to make decisions by estimating the long-term value of different actions.
What's included
- Definition and types of value functions
- State value functions
- Action value functions
- Bellman equation
- Optimal value functions
- Value iteration
- Policy iteration
- Q-learning
- SARSA
- Applications of value functions
Keywords
- Value Functions
- Reinforcement Learning
- State Value Functions
- Action Value Functions
- Bellman Equation
- Optimal Value Functions
- Value Iteration
- Policy Iteration
- Q-Learning