OhhO Train
Turn demonstrations into policies.
OhhO Data collects the demonstrations; OhhO Serve runs the model — Train is the engine in between. Fine-tune Vision-Language-Action, imitation-learning and reinforcement-learning policies from your own episodes or in simulation, track every run, and export a deployment-ready checkpoint.
- RL policy ONNX export script in the public repositoryEvidence
- Tiny ACT CPU training on the OHH-86 sim loop (once a run is green)
- Prototype training console — simulated run UI
- Vision: VLA fine-tune, diffusion, SmolVLA, OpenVLA
- Vision: continual learning, W&B sweeps, Fleet ONNX OTA
Simulated data — connect a robot via Connect for live data
Concept render — not footage of OmniBot
Works today
- Reinforcement learning policy ONNX export script in public repositoryEvidence
In progress
Vision: not built
Turn demonstrations into policies.
OhhO Data collects the demonstrations; OhhO Serve runs the model — Train is the engine in between. Fine-tune Vision-Language-Action, imitation-learning and reinforcement-learning policies from your own episodes or in simulation, track every run, and export a deployment-ready checkpoint.
- Methods
- BC, VLA fine-tune, ACT, diffusion, offline + online RL
- Data sources
- OhhO Data (LeRobot), Gazebo, Isaac Sim
- Dexterity
- Position-controlled pick-and-place today; force limiting, tactile feedback & in-hand manipulation (Vision: not built)
- Foundation
- Open-source OmniVLA engine
- Tracking
- Weights & Biases + Bayesian sweeps
- Hardware
- Your GPU — we help you size it or recommend a rig
- Export
- Serve checkpoint + ONNX for Fleet OTA
Works better together
Ready to build with OhhO Train?
The engine and this console demo are free. Hosted cloud is a waitlist, not a checkout.