open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-04-19 12:58:07 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Changed parmas back in puzzle24

Browse source
This commit is contained in:
abdulhakeem 2025-04-03 08:46:18 -05:00
parent f202e4f7f2
commit 29ec970044
1 changed files with 3 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

4
reasoning_gym/games/puzzle24.py
View file

@ -24,7 +24,7 @@ DATASET_NAME = "puzzle24"
class Puzzle24Config: class Puzzle24Config:
operators: tuple = ("+", "-", "*", "/") operators: tuple = ("+", "-", "*", "/")
min_value: int = 1 min_value: int = 1
max_value: int = 6 max_value: int = 10
seed: Optional[int] = None seed: Optional[int] = None
size: int = 500 size: int = 500
@ -116,8 +116,10 @@ class Puzzle24Dataset(ProceduralDataset):
try: try:
answer = answer.strip() answer = answer.strip()
user_answer = int(parse_expr(answer)) user_answer = int(parse_expr(answer))
print(f"User answer: {user_answer}")
solved = user_answer == 24 solved = user_answer == 24
used_numbers = [int(num) for num in re.findall(r"\b\d+\b", answer)] used_numbers = [int(num) for num in re.findall(r"\b\d+\b", answer)]
print(f"Used numbers: {used_numbers}")
if len(used_numbers) != 4: if len(used_numbers) != 4:
reward = 0.01 reward = 0.01
elif any(num > self.config.max_value or num < self.config.min_value for num in used_numbers): elif any(num > self.config.max_value or num < self.config.min_value for num in used_numbers):