563 commits

Author	SHA1	Message	Date
Andreas Koepf	6bf2dfa36c	formatting	2025-02-16 16:18:39 +01:00
joesharratt1229	35fe482c4d	updated spell backward impl	2025-02-16 13:10:26 +00:00
joesharratt1229	1c930a5e23	added custom score answer func	2025-02-16 13:10:03 +00:00
joesharratt1229	cc7d422d78	merged remoted ... Merge remote-tracking branch 'origin/main' into feat/score-answer-impl	2025-02-16 12:03:25 +00:00
joesharratt1229	569517664f	corrected failing airthmetic test	2025-02-16 12:01:54 +00:00
Andreas Koepf	c7b41acf14	add configuration option for ArcAgiDataset	2025-02-16 12:49:21 +01:00
Andreas Köpf	0b7d55c7b4	Merge pull request #138 from zafstojano/fix/palindrome ... fix(env): Palindrome	2025-02-16 11:38:39 +01:00
Zafir Stojanovski	4b71eb2da9	improve template	2025-02-16 11:02:51 +01:00
joesharratt1229	a59e4cc918	reformatted prompt	2025-02-16 09:27:21 +00:00
joesharratt1229	c28688cb96	reformatted basic airth question template	2025-02-16 09:07:56 +00:00
Ubuntu	d9b08a579e	reformatted word ladder question template	2025-02-16 09:04:17 +00:00
Zafir Stojanovski	b9bd7a1162	fix leg counting prompt template	2025-02-16 09:58:36 +01:00
Andreas Koepf	ac1f889d83	import FutoshikiDataset & update GALLERY	2025-02-15 21:26:15 +01:00
Andreas Köpf	ddb334ba20	Merge pull request #60 from olliestanley/feature/futoshiki-generator ... Add Futoshiki puzzle generator	2025-02-15 21:24:15 +01:00
Andreas Köpf	c4a4300029	Merge pull request #135 from zafstojano/fix/power-function ... fix(env): Power Function	2025-02-15 21:20:51 +01:00
Andreas Köpf	a409cf3778	Merge pull request #134 from zafstojano/fix/string-insertion ... fix(env): String Insertion	2025-02-15 21:20:05 +01:00
Andreas Köpf	53bb55c26c	Merge pull request #133 from zafstojano/fix/binary-matrix ... fix(env): Binary Matrix	2025-02-15 21:19:23 +01:00
Zafir Stojanovski	662c4e16c2	fix prompts	2025-02-15 20:59:07 +01:00
Zafir Stojanovski	b5f5733052	update system prompt	2025-02-15 17:41:05 +01:00
Zafir Stojanovski	467300f7f9	fix score function	2025-02-15 17:40:37 +01:00
Zafir Stojanovski	815b3c4ee5	test for parsing answer as python list	2025-02-15 16:14:13 +01:00
Zafir Stojanovski	95d367bc17	fix score function and add test	2025-02-15 16:09:08 +01:00
Zafir Stojanovski	0db8012e88	duplicate answer word	2025-02-15 15:38:56 +01:00
Zafir Stojanovski	87ae218328	update binary matrix prompt	2025-02-15 15:34:38 +01:00
Zafir Stojanovski	b7b8e90d04	update system prompt to tell model to follow 1-shot example format	2025-02-15 15:34:30 +01:00
Oliver	d42b84ef4c	Add more instruction to generated questions	2025-02-15 13:47:54 +00:00
Zafir Stojanovski	b8036a4b7d	fix prompt	2025-02-15 10:31:03 +01:00
Andreas Koepf	82ebcf4ac6	bump version, update GALLERY.md	2025-02-14 23:34:59 +01:00
Andreas Köpf	2c56960ff8	Merge pull request #113 from Iron-Bound/rush_hour ... Rush Hour Gym	2025-02-14 23:32:51 +01:00
Andreas Koepf	14f67cb7e7	fix handling of walls, add unit test	2025-02-14 23:29:17 +01:00
Zafir Stojanovski	f9e846871b	Merge branch 'main' of https://github.com/open-thought/reasoning-gym into env/string-splitting	2025-02-14 17:51:18 +01:00
Zafir Stojanovski	60ebb1329d	string splitting	2025-02-14 17:50:07 +01:00
Andreas Koepf (aider)	e106bd311c	refactor: Use Path.open() to read rush_18k.txt line by line	2025-02-14 17:41:09 +01:00
Andreas Koepf	1d1a0367d4	add RushHour to games/__init__.py	2025-02-14 17:35:14 +01:00
Andreas Koepf (aider)	d5ce2bfdf5	feat: Add score_answer method to RushHourDataset with input validation	2025-02-14 17:33:01 +01:00
Andreas Koepf (aider)	8278a9521c	test: Add comprehensive unit tests for RushHourDataset	2025-02-14 17:29:43 +01:00
Andreas Koepf (aider)	0eecc6c450	feat: Add RushHourConfig and RushHourDataset for procedural Rush Hour puzzle generation	2025-02-14 17:26:24 +01:00
Andreas Koepf	254f866146	refactor: Remove commented TODOs and example code from rush_hour.py	2025-02-14 17:26:22 +01:00
Andreas Koepf	417e71cd17	add unit test for RushHour Board::perform_moves()	2025-02-14 16:59:19 +01:00
Andreas Köpf	2d38493a55	Merge pull request #128 from open-thought/rich/scorefixes ... [Ongoing] Eval Template and Score Fixes	2025-02-14 16:15:37 +01:00
ironbound	bcf6344125	input check	2025-02-14 16:00:22 +01:00
Andreas Koepf	4ddd04a825	incorporate prompt changes suggested by Miserlou	2025-02-14 15:44:00 +01:00
Andreas Koepf	2726caf2fe	ignore single whitespace at beginning and end of answer, use reward = len(oracle_answer) / len(answer)	2025-02-14 15:40:12 +01:00
Iron-Bound	4fffde10f4	Merge branch 'open-thought:main' into rush_hour	2025-02-14 15:31:17 +01:00
Rich Jones	28d89df935	word sorting score func	2025-02-14 12:57:31 +01:00
Rich Jones	ce3e9bebea	prompts - no reasoning in answers	2025-02-14 12:42:24 +01:00
Rich Jones	b3438d9976	fix letter jumble	2025-02-14 12:21:56 +01:00
Rich Jones	f945bc5d88	lint	2025-02-14 12:17:50 +01:00
Rich Jones	ab51228f35	clean up ransom note	2025-02-14 12:15:55 +01:00
Rich Jones	02c1fdf304	explicitly handle multiple solutions	2025-02-14 12:07:53 +01:00