Skip to content

Op model16 deep#38073

Open
haraschax wants to merge 8 commits into
masterfrom
op_model16_deep
Open

Op model16 deep#38073
haraschax wants to merge 8 commits into
masterfrom
op_model16_deep

Conversation

@haraschax
Copy link
Copy Markdown
Contributor

@haraschax haraschax commented May 20, 2026

WORKS NOW

@github-actions
Copy link
Copy Markdown
Contributor

Model Review

master PR branch
driving_off_policy.onnx N/A (new model) 1c8e05fa-bb24-42ad-af22-c0e6d59a5df5
driving_vision.onnx 6a7d09ad-bcc9-43bc-916d-29287e60cee2 1c8e05fa-bb24-42ad-af22-c0e6d59a5df5
driving_on_policy.onnx N/A (new model) 1e72cf5a-785f-45ea-888f-28cdb14785de

@github-actions
Copy link
Copy Markdown
Contributor

github-actions Bot commented May 20, 2026

Process replay diff report

Replays driving segments through this PR and compares the behavior to master.
Please review any changes carefully to ensure they are expected.

✅ 0 changed, 66 passed, 0 errors

@haraschax haraschax force-pushed the op_model16_deep branch 8 times, most recently from da19d39 to fe3df6e Compare May 20, 2026 22:28
@commaci-public
Copy link
Copy Markdown
Contributor

commaci-public commented May 21, 2026

@haraschax haraschax marked this pull request as draft May 21, 2026 04:50
haraschax and others added 6 commits May 22, 2026 22:31
Split the driving model into vision + off_policy + on_policy ONNX
files and wire up the RL policy:

- 3-file model split (vision / off_policy / on_policy), replacing the
  combined big_driving_policy/vision models
- compiler updates for the split models
- actually consume the policy action in modeld
- add desire state to the driving model
- model iterations (smoothness, off/on-policy weight updates)
@haraschax haraschax marked this pull request as ready for review May 24, 2026 03:08
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants