Scaling Behavior Cloning Games

Train video game-playing foundation models discovering that increasing training data and network depth enables learning more causal policies. Release 8300+ hours of gameplay data and open-source models for real-time consumer GPU inference.

adu2021 809798f 1.5 KB Updated

File contents

adu2021/skillxiv/tree/main/skills/skillxiv-v0.0.2-claude-opus-4.6/scaling-behavior-cloning-games commit 809798f432

Frequently asked questions

npx skillmds@latest add adu2021/scaling-behavior-cloning-games