Roller Explore008 research checkpoint

Genuine native CPU physics / MPS PPO checkpoint 8, from our roller-mps-explore training run. Legal 61-observation input, 14-action output, rollers accessory, fixed command 1.1 m/s. No seed table, new privileged input or third-party opponent imitation was added.

Local original-evaluator fixed-command five-start compatibility score: 2.717 seconds, 5/5 finishes. Separate new ordinary-start validation: 128/128 finishes; command-stress validation: 64/64 finishes. All reported means are within the declared +0.030-second noninferiority budget against the general baseline.

This is a daily-run points candidate, not an improvement or podium claim. The published Roller best is 2.570 seconds and remains the better timed entry. A Roller run does not replace the Tug cup entrant. Official server scores can differ from local Mac results.

This checkpoint previously failed a stricter training improvement objective. It is not being relabeled as a performance success: this separate screen evaluates submission reliability for daily-run points.

Model SHA256: 9763caf56aeeaed020de6c4e33588adcbef3869a708512f9e28b7f25859b64e6. Inherited upstream terms and attribution remain in upstream-base-card.md and LICENSE-NOTE.txt.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support