open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-04-22 16:49:06 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

[Env] Game of Life Halting Prediction (#272)

Browse source 
This is a variant of the Game of Life task, which rather than trying to test the algorithmic simulation, tests the ability of the model to do explanatory reasoning of the board. The idea is that a model with good explanatory reasoning will be able to see that a game will not halt without simulating it into the future.

The task presents a GoL board, and the model is asked to predict if the board will halt (die, all cells zero) after n steps. Sometimes, the board will be made up of 'oscillators', isolated structures which never die. Othertimes, it is filled with non-oscillators, structures which will always die after a few steps. The model should deduce which case the presented board is.
This commit is contained in:
Rich Jones 2025-03-07 10:05:12 +01:00 • committed by GitHub
parent 862617b7e0
commit 07dc01ad87
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 420 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
reasoning_gym/algorithmic/game_of_life.py
View file

@ -10,7 +10,7 @@ from ..factory import ProceduralDataset, register_dataset
@dataclass
class GameOfLifeConfig:
"""Configuration for sudoku puzzle generation"""
"""Configuration for Game of Life puzzle generation"""
grid_size_x: int = 10
grid_size_y: int = 10