AI engineering glossary · Reinforcement learning
What is dyna?
Dyna: A model-based architecture that combines real experience with simulated experience generated by a learned model. The same update rule learns from both, so each real step yields many extra learning steps.
Dyna: an example
After each real step, do 10 extra Q-updates on transitions imagined from the learned model.
Related terms
More Reinforcement learning terms
- Dynamic programming (reinforcement learning)
- Eligibility trace
- Entropy regularisation
- Environment
- Episode
- Episodic task
- Epsilon-greedy
- Experience replay
Where you learn it
Dyna is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.