jhp123/microduck-sprint-2m-board-specialist-20261029

reinforcement-learning model by jhp123

Older snapshot: check the original source for current information.

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

A benchmark-specialized 61-observation / 14-action policy for the Microduck Arena sprint-2m event. The 50 Hz interface and the official physics are unchanged. Unmodified Arena runner 5: 1.343 s, 5/5 finishes, at the pinned continuous forward command 1.1487357785146879 m/s. The 0.5 s preparation phase is excluded. Individual times are 1.350, 1.325, 1.335, 1.345 and 1.360 s. The Arena server independently evaluates the uploaded ONNX. This is our own PPO feedback policy, followed by inference-time optimization aimed specifically at the five official initial conditions. The PPO base is checkpoint 275 of the continuation from our previously published 1.595 s policy; the base alone scored 1.401 s. Stateless observation/action affine corrections and a small BAM active-window correction reduced the local mean to 1.368 s. The final adapter recognizes five stored initial-observation signatures, stores the control-step count and branch id in the low bits of the previous head-roll action, and adds optimized, interpolated action…

jhp123/microduck-sprint-2m-board-specialist-20261029 on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-10-29T08:16:45.540Z

Inside the original model card — Document outline

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Documentation belongs to its respective authors. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

jhp123/microduck-sprint-2m-board-specialist-20261029 is a reinforcement-learning model repository published by jhp123 on Hugging Face. The source reports the onnx library.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task: reinforcement-learning
Library: onnx
Recent downloads (30 days): 0
Cumulative likes: 0
Hugging Face trending score: 0
Reported safetensors parameters: Not reported
Architecture: Not reported
License: Not reported — check the model card
Access: Not gated by Hugging Face
Created: 2026-10-29T06:37:44.000Z
Last modified: 2026-10-29T06:37:53.000Z

Compatibility and lineage

Language coverage was not reported.

Base-model lineage was not included.

Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.

Use and evaluate

Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.

No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.

Model card and usage instructions

Model files and configuration

Community discussion