π0.6 (pi-0.6)
Physical IntelligenceRobotic manipulation
The π0.6 (pi-0.6) model is a robotic manipulation model from Physical Intelligence with 5260000000.0 parameters.
About π0.6 (pi-0.6)
We study how vision-language-action (VLA) models can improve through real-world deployments via reinforcement learning (RL). We present a general-purpose method, RL with Experience and Corrections via Advantage-conditioned Policies (RECAP), that prov
Details
- Provider
- Physical Intelligence
- Task
- Robotic manipulation
- Parameters
- 5260000000.0
- Released
- 2025-11-17
- Open weights
- No