roller-improver-rev3

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

A remix of jrubiosainz/microduck-game-roller-remix6 (revision ef9cba565): DenRakEiw senate_duck_0904's seed-5 delta branch ported in (as in our roller-improver v4), plus our seed-1 slot table and an antithetic-ES step. The network is frozen; strength, gear and mass are untouched. Seed-5 branch credit: DenRakEiw/microduck-senate_duck_0904. Search found by antithetic ES on box CPU, checked with a real ONNX rollout.

Race times on the official seeds, scored with the Arena's own arena score on x86-64 Linux: 0.92, 0.90, 0.90, 0.90, 0.90 s, a 0.904 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 b5621234d92805830b1ab641d894a5734845fe680402a4dd8131d777d6a9dc1c. 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.