AI engineering glossary · Reinforcement learning
What is discount factor?
Discount factor (also called Gamma): A number between 0 and 1 that reduces the weight of scores received further in the future. A value near 0 makes the learner short-sighted, and a value near 1 makes it patient. It also keeps totals finite in never-ending problems.
Discount factor: an example
With gamma = 0.99, a reward of 100 that arrives 50 steps later counts for about 100 * 0.99^50 = 60.5 today; with gamma = 0.9 it counts for only 0.5.
Related terms
More Reinforcement learning terms
- Distributional reinforcement learning
- Double DQN
- Double Q-learning
- Dueling network
- Dyna
- Dynamic programming (reinforcement learning)
- Eligibility trace
- Entropy regularisation
Where you learn it
Discount factor is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.