avaskys/skat-ml-models
By avaskys · ↓ 0 · ♥ 0 · Updated 2026-02-27
What's in this repo
This page lists the files in avaskys/skat-ml-models, including bidding_dense.onnx, bidding_transformer.onnx, card_play_transformer.onnx and more.
- 5 ONNX models (.onnx files)
- 14 files, including 5 .onnx, 4 .data, 3 .json, 1 .md
- Last updated 2026-02-27
ONNX files
| File | Size | Download |
|---|---|---|
| bidding_dense.onnx | — | Download |
| bidding_transformer.onnx | — | Download |
| card_play_transformer.onnx | — | Download |
| game_eval_dense.onnx | — | Download |
| game_eval_transformer.onnx | — | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
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 |
Gameplay Phases
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.
Model Details
| Model | Input | Output |
|---|---|---|
| BiddingEvaluator | 35 features (10 cards + position) | 63 × 2 win probs (pickup/hand) |
| BiddingTransformer | 10 card indices + position | 63 × 2 win probs (pickup/hand) |
| GameEvaluator | 75 features (hand + skat + context) | 1 win probability |
| GameEvaluatorTransformer | Card indices + context | 1 win probability |
| CardPlayTransformer | Sequence of moves | 32 card logits |
Interface Specification
The interface/ directory defines the contract for using these models:
feature_spec.json— Card encoding, game type encoding, input/output tensor shapestest_vectors.json— Reference inputs and expected outputs for validation
Use these to ensure your implementation encodes inputs correctly.
Usage
Load with ONNX Runtime in any supported language (Python, Java, C++, etc.):
import onnxruntime as ort
session = ort.InferenceSession("bidding_transformer.onnx")
Training
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.
License
MIT
Model info
Created: 2026-02-27
Updated: 2026-02-27
View on Hugging FaceFiles (14)
Related models
More from avaskys
No other models by this author.
More models
No task type declared.