sable-r/checkers-zero-lite
Reinforcement learning4M paramssafetensorsLicense: mit#self-play#board-games
Updated Aug 15, 2026
Part of the Open Pace seed catalog. Weights are listed for the preview and become downloadable at launch.
Overview
A self-play checkers agent with a small policy-value network.
sable-r/checkers-zero-lite is a 4M-parameter reinforcement learning model, published in safetensors under the mit license.
Intended use
- Reinforcement learning in the domains described above.
- Research, prototypes and products that keep a person in the loop.
- Fine-tuning as a starting point for a narrower task.
How to use
# Command-line client (planned; the shape may change)
pace pull sable-r/checkers-zero-lite
# Python (planned)
from openpace import load
model = load("sable-r/checkers-zero-lite")Limitations
- The agent only knows the environments it was trained in. Small rule changes can break it.
License
Released under mit. Read the license file before using the weights commercially.