Upload README.md with huggingface_hub

59618f7 verified about 2 months ago

2.44 kB

library_name: onnxruntime
license: mit
tags:
  - skat
  - card-game
  - onnx
language:
  - en

Skat ML Models

Models for playing the German card game Skat, trained on ~9 million games from the International Skat Server (ISS).

Models

Model	Architecture	Description	Size
`bidding_dense`	Dense ResNet	Pre-skat bidding evaluation	~9 MB
`bidding_transformer`	Transformer	Pre-skat bidding with attention	~14 MB
`game_eval_dense`	Dense ResNet	Post-skat game type selection	~9 MB
`game_eval_transformer`	Transformer	Post-skat evaluation with attention	~13 MB
`card_play_transformer`	Transformer	Card play selection	~72 MB

Skat has three decision phases, each with its own model:

Bidding — "Can I win at bid level X?" Evaluates win probability across all 63 bid levels.
Game selection — "Which discards + game type maximize win probability?" Evaluates after winning the bid.
Card play — "Which card should I play?" Selects from legal cards during tricks.

The interface/ directory defines the contract for using these models:

feature_spec.json — Card encoding, game type encoding, input/output tensor shapes
test_vectors.json — Reference inputs and expected outputs for validation

Use these to ensure your implementation encodes inputs correctly.

Load with ONNX Runtime in any supported language (Python, Java, C++, etc.):

import onnxruntime as ort

session = ort.InferenceSession("bidding_transformer.onnx")

Models were trained with rating-weighted loss using ISS player ELO ratings, so decisions from stronger players contribute more to the learned policy.

For training code and details, see the GitHub repository.

MIT