iviazovetskyi/enclosure-v1

Enclosure v1

Policy and value network for Enclosure, trained by self-play.

Code: https://github.com/iviazovetskyi/EnclosurePublic

Self-play games: https://huggingface.co/datasets/iviazovetskyi/enclosure-public

model.pt is a PyTorch checkpoint with keys cfg, model, and step. The optimizer state is not included.

• Architecture: 10 residual blocks, 128 channels, about 3.3 million parameters (version 1).
• Training step: 351400.

i8-s32.wasm is a Constellation bot with int8 weights and 32 playouts. It was built from the step 350000 checkpoint, 1,400 steps before model.pt.

Load the checkpoint with the bot server:

python rl/server.py

The server downloads this file on startup. A local .pt path also works.

License

MIT. See the GitHub repository.