open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-04-25 17:10:51 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

catch exception in RubiksCube score_answer

Browse source
This commit is contained in:
Andreas Koepf 2025-01-30 10:25:04 +01:00
parent a04db556e6
commit a6bf23e655
1 changed files with 10 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

7
reasoning_gym/cognition/rubiks_cube.py
View file

@ -102,21 +102,24 @@ class RubiksCubeDataset(ProceduralDataset):
def score_answer(self, answer: Optional[str], entry: Dict[str, any]) -> float: def score_answer(self, answer: Optional[str], entry: Dict[str, any]) -> float:
"""Determine if the solution provided solves the cube""" """Determine if the solution provided solves the cube"""
answer = answer.strip()
reward = 0.0 reward = 0.0
if answer is not None: if answer is not None and len(answer) > 0:
# Reconstruct the test cube # Reconstruct the test cube
eval_cube = Cube(entry["metadata"]["cube_size"]) eval_cube = Cube(entry["metadata"]["cube_size"])
eval_cube.rotate(entry["metadata"]["scramble_moves"]) eval_cube.rotate(entry["metadata"]["scramble_moves"])
# Test the solution # Test the solution
try:
eval_cube.rotate(answer) eval_cube.rotate(answer)
solved = eval_cube.is_done() solved = eval_cube.is_done()
if solved: if solved:
reward = 1.0 reward = 1.0
else: else:
reward = 0.1 # Incorrect, but rotate could parse the answer
except:
reward = 0.01 # At least you tried reward = 0.01 # At least you tried
return reward return reward