open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-04-28 17:29:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix Rush Hour (#336)

Browse source 
* think it fixes rush hour

* explain walls
This commit is contained in:
Rich Jones 2025-03-13 20:42:40 +01:00 • committed by GitHub
parent cad255e31b
commit fe0f9ae114
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 13 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

14
tests/test_rush_hour.py
View file

@ -30,7 +30,7 @@ def test_rush_hour_deterministic():
def test_rush_hour_items():
"""Test basic properties of generated items"""
config = RushHourConfig(min_moves=1, max_moves=10, size=10, seed=42)
config = RushHourConfig(min_moves=1, max_moves=10, size=18000, seed=42)
dataset = RushHourDataset(config)
for i in range(len(dataset)):
@ -73,27 +73,31 @@ def test_score_answer():
# Test invalid answers
assert dataset.score_answer(None, puzzle) == 0.0
assert dataset.score_answer("", puzzle) == 0.0
assert dataset.score_answer("invalid", puzzle) == 0.0
assert dataset.score_answer("A+1 B-2 INVALID", puzzle) == 0.0
assert dataset.score_answer("invalid", puzzle) == 0.01
assert dataset.score_answer("A+1 B-2 INVALID", puzzle) == 0.01
# Test incomplete solution
assert dataset.score_answer("A+1 B-2", puzzle) == 0.0
assert dataset.score_answer("A+1 B-2", puzzle) == 0.01
def test_perform_moves():
b = Board("GBBoLoGHIoLMGHIAAMCCCKoMooJKDDEEJFFo")
assert not b.solved
incomplete_moves = "F+1 K+1 M-1 C+3 H+2 J-1 E+1 G+3 B-1 I-1 A-3 I+1 L+1 B+3 I-1 A+2 G-3"
b.perform_moves(incomplete_moves)
assert not b.solved
incomplete_moves = "X+1 \n Y+22"
b.perform_moves(incomplete_moves)
assert not b.solved
solution = "E-1 H-3 A-1 J+1 C-3 M+1 B+1 K-4 A+1 C+2 D-1 F-1 H+3 A-1 K+1 B-1 M-1 C+1 J-1 E+1 G+3 A-1 I+1 B-3 I-1 A+1 G-1 E-1 J+1 C-1 K-1 L-1 M+3 A+3"
b.perform_moves(solution)
assert b.solved
def test_perform_moves_walls():
## ?? This test is incomplete. I don't know why.
b = Board("BBoIKxCCCIKoGAAJooGoHJDDooHEELoFFoxL")
print(b.board_str())
# assert sum(1 for p in b._pieces if p.fixed) == 2, "two walls expected"
# assert not b.solved