---
license: other
library_name: pytorch
tags:
  - robotics
  - reinforcement-learning
  - rainbow-dqn
  - speed-control
  - metarobobench
---

# MetaRoboBench Speed-Control Heads

Offboarding archive of Rainbow DQN, CQL, and candidate-value heads trained for chunk-level Fast/Normal/Slow selection on top of Pi05 checkpoint `21650`.

The primary model is `rainbow/shared_all50_final/models/shared_all50.pt`:

- 50-task shared Rainbow head
- 100,491 decisions and 99,962 updates
- 1,941/2,500 successes = 77.64%
- Fast/Normal/Slow chunk shares = 38.6/32.3/29.1%
- Mean speed switches = about 4.23 per episode

The accelerated shared checkpoint is a distinct earlier checkpoint, not a duplicate. Per-task Rainbow, CQL, and candidate-value models are retained as baselines and negative-result artifacts.

Code reference:

- Repository: https://github.com/MMMM3202/MetaRoboBench
- Branch: `codex/vlm-rainbow-shared-20260821`
- Commit: `5b36567f0c6174ad82a3d4c669134f7b28acc945`

See `MODEL_MANIFEST.md` for the full inventory and result caveats.