koskokos/rush-soldier

reinforcement-learning model by koskokos

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 soldier network for rush, a 2D team shooter for 500 v 500 battles with control points (code, world, viewer and training: https://github.com/MedDevSystems/rush-arena). One network plays every soldier of an army, all 8 classes (the class is part of the observation). The army is commanded by the heuristic army commander of the rush package (respawn points, which control point each squad of 8 takes); the network observes its order and fights. Per soldier and decision (every 4 frames at 60 fps): a transformer over entity tokens (nearest allies and enemies, bullets, control points, last-seen enemies, wall grids), an LSTM, and a state-conditioned attention readout over further tokens (up to 56 soldiers, the 32 most dangerous bullets, a 17 × 17 coarse map of the battle); four action heads — move (9), fire (2), turn (7, fine and coarse), dash (2) — masked by the rules. 1.7 M parameters. config.json carries…

koskokos/rush-soldier on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-09-29T07:55:11.541Z

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. Reported project/model license: mit. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

koskokos/rush-soldier is a reinforcement-learning model repository published by koskokos on Hugging Face. The source reports the pytorch 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: pytorch
Recent downloads (30 days): 0
Cumulative likes: 0
Hugging Face trending score: 0
Reported safetensors parameters: 1,677,947
Architecture: Not reported
License: mit
Access: Not gated by Hugging Face
Created: 2026-09-29T06:36:57.000Z
Last modified: 2026-09-29T06:37:03.000Z

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