AI engineering glossary · Reinforcement learning
What is sim-to-real transfer?
Sim-to-real transfer (also called Sim2real): Training a decision rule in a simulator and then deploying it on real hardware. It is cheaper and safer than real-world trials, but the gap between simulator and reality can make the rule fail unless it is made robust.
Sim-to-real transfer: an example
A robot hand is trained on billions of simulated steps and then run on a physical hand.
Related terms
- Domain randomisation
- World model
- Sample efficiency
- Model-based
More Reinforcement learning terms
Where you learn it
Sim-to-real transfer is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.