hill-improver-rev3

An entry for Hill Climb of the Microduck Arena. Simulation only.

A remix of jrubiosainz/microduck-game-hillclimber-remix6 (revision 2433eab15): our own seed-4 delta-table rows (slot 4) from a table search plus a second, independently drawn antithetic-ES step. The network is frozen; strength, gear and mass are untouched. 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: 0.74, 0.76, 0.74, 0.76, 0.76 s, a 0.752 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 8627a84963aa2a869c600fe75dc2b774a59a9d8044bf38e20136f095e8a54df6. 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.