open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-05-02 17:45:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
reasoning-gym/reasoning_gym/games
History
Zafir Stojanovski d26663fb3f
Fix impossible_ratio not being respected in knight_swap (#521) (#524) 
Move make_impossible decision before the retry loop so it's fixed per
item instead of re-rolled on every attempt, which skewed the actual
ratio of impossible puzzles well above the configured value.
2026-03-27 15:18:08 +00:00
..
contrib added sokoban dataset (#325) 2025-03-11 00:21:03 +01:00
__init__.py add survo env (#461) 2025-06-08 11:56:33 +01:00
boxnet.py fix boxnet scoring function (#420) 2025-04-14 20:44:24 +01:00
countdown.py Fix(reasoning_gym/games/countdown): Resolve SymPy parsing conflict for 10+ input numbers (#514) 2025-12-15 11:05:38 +00:00
emoji_mystery.py fix(curriculum): Make boundaries in curriculum more sensible (#407) 2025-04-04 20:24:14 +02:00
futoshiki.py make task entries json serializable (#443) 2025-06-02 08:57:15 +02:00
kakurasu.py add kakurasu env (#460) 2025-06-08 09:20:53 +01:00
knight_swap.py Fix impossible_ratio not being respected in knight_swap (#521) (#524) 2026-03-27 15:18:08 +00:00
mahjong.py fix(envs): Add source dataset and index to metadata (#388) 2025-03-20 11:12:14 +00:00
maze.py Add assertion for maze constraints and limit _random_floor_cell attempts (#515) 2026-01-16 09:56:39 +01:00
mini_sudoku.py fix(curriculum): Make boundaries in curriculum more sensible (#407) 2025-04-04 20:24:14 +02:00
n_queens.py fix(curriculum): Make boundaries in curriculum more sensible (#407) 2025-04-04 20:24:14 +02:00
puzzle24.py make task entries json serializable (#443) 2025-06-02 08:57:15 +02:00
rush_hour.py fix(curriculum): Make boundaries in curriculum more sensible (#407) 2025-04-04 20:24:14 +02:00
sokoban.py Feat/intragen experiments (#414) 2025-04-16 08:04:52 +02:00
sudoku.py fix(curriculum): Make boundaries in curriculum more sensible (#407) 2025-04-04 20:24:14 +02:00
survo.py add survo env (#461) 2025-06-08 11:56:33 +01:00
tower_of_hanoi.py fix boxnet scoring function (#420) 2025-04-14 20:44:24 +01:00
tsumego.py fix(curriculum): Make boundaries in curriculum more sensible (#407) 2025-04-04 20:24:14 +02:00