AI engineering glossary · Reinforcement learning
What is C51 (distributional reinforcement learning)?
Distributional reinforcement learning (also called C51, Distributional RL): A family of methods that learn the full probability distribution of returns rather than only their average. Keeping the spread captures risk and often gives better learning signals in deep networks.
Distributional reinforcement learning: an example
The C51 method represents the return distribution with 51 fixed support points.
Related terms
More Reinforcement learning terms
- Double DQN
- Double Q-learning
- Dueling network
- Dyna
- Dynamic programming (reinforcement learning)
- Eligibility trace
- Entropy regularisation
- Environment
Where you learn it
Distributional reinforcement learning is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.