A fruit-fly brain playing Beat Saber (replay + reinforcement learning)
X ● Covered by 2 sources
A fruit-fly brain connectome was trained to play Beat Saber using replay data and reinforcement learning. The training specifically uses replay signals so movements that score well are reinforced. The next training stage aims to reduce reliance on replays so the brain model can react on its own.
Why it matters
The creator used replay data plus reinforcement learning to teach the connectome which movements score well. The current version still gets help from replay signals while training aims to make it react on its own.
Related stories
Fly Language Model (FLM) Wires the Full Fruit Fly Connectome Into a Frozen 1.2B LLM, and Its Own Controls Show the Wiring Does Not Help
MarkTechPost · 2 days ago ·
12
A connectomics milestone: Mapping the complete male fruit fly brain
Google Research · 1 week ago ·
25
Just like a fruit fly, a new algorithm never forgets old scents
Ars Technica · 1 week ago ·
39