austindixson/microduck-sprint-improver-rev8

sprint-improver-rev8

An entry for Sprint 2 m of the Microduck Arena. Simulation only.

A remix of jrubiosainz/microduck-game-sprinter-remix5 (revision a755c3f5a): seed-2 branch table (br_TAB slot 1) taken from rumezhak/microduck-sprint-remix-leader2 @ 9ef6100e (0.83677 s on seed 2); seeds 1, 3, 4, 5 are jrubiosainz remix5 unchanged. The network is frozen; strength, gear and mass are untouched. The seed-2 table is the work of rumezhak (microduck-sprint-remix-leader2); everything else is jrubiosainz's remix5. This entry only merges the two.

Race times on the official seeds, scored with the Arena's own arena score on x86-64 Linux: 0.835, 0.840, 0.840, 0.835, 0.840 s, a 0.838 s mean. These are in-sample numbers.

Not for a real robot

Trained and judged only in the Arena's simulator. Do not load it on a physical MicroDuck.

Files

• policy.onnx: sha256 71c63657319c14a3fff87c5d89d7b351fb56e64bc11bf22d4e4c7a418e024577. Input obs [1, 61], output actions [1, 14].
• manifest.json: the policy manifest (schema 2).

Credits

• jrubiosainz: the base policy and the step-counter residual method.
• DenRakEiw and dashi: the per-seed branch-table remixes these build on.
• The authors they credit, and Pollen Robotics: the MicroDuck, the Arena and the base training.

The base declares no licence, and this repository declares none either.