100-task BEHAVIOR-1K (2026) meta-training pipeline for a pi-0.5 VLA policy on 8x B300. Extends the 50-task BEHAVIOR-Challenge-winning checkpoint to 100 activities.
-
Updated
Aug 25, 2026 - Python
#
behavior-1k
Here are 2 public repositories matching this topic...
Closed-loop benchmark of 9 VLA policies (GR00T N1.7, pi0/openpi, LoRA vs full fine-tuning) on BEHAVIOR-1K. Imitation learning / behavioral cloning with diffusion action heads in PyTorch, plus a reproducible eval harness, unattended training automation, and raw metrics.
benchmark pytorch transformer behavioral-cloning lora imitation-learning vla humanoid-robot robot-learning fine-tuning pi0 robot-manipulation openpi diffusion-policy vision-language-action lerobot gr00t closed-loop-evaluation omnigibson behavior-1k
-
Updated
Aug 3, 2026 - Python
Improve this page
Add a description, image, and links to the behavior-1k topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the behavior-1k topic, visit your repo's landing page and select "manage topics."