Commit graph

509 commits

Author SHA1 Message Date
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 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
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
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
Andreas Koepf
92ffda4b8b lazy import of wordle_words 2025-02-14 12:06:44 +01:00
Andreas Koepf
ee2c03ea65 import string_insertion, minor whitespace fixes, gallery update 2025-02-14 07:55:38 +01:00
Andreas Koepf
80719c7201 move game_of_life from games to algorithmic 2025-02-14 07:26:47 +01:00
Andreas Köpf
3ceb7310ca Merge pull request #126 from zafstojano/env/string-synthesis
String Synthesis
2025-02-14 07:11:25 +01:00
Andreas Köpf
25e7bf140a Merge branch 'main' into rich/graphcolor 2025-02-14 07:09:38 +01:00
abdulhakeem
2dad5a56f3 Remove play file and format with pre-commit 2025-02-13 22:39:21 -06:00
Adefioye
0738d3fd17 Merge branch 'main' into koko/eval 2025-02-13 22:27:16 -06:00
abdulhakeem
b2ca8016fb Fix formatting of added instructions 2025-02-13 21:26:58 -06:00
abdulhakeem
09ea24d84d Fix more conflict 2025-02-13 21:26:54 -06:00
abdulhakeem
3b1ab9eb86 Fix more conflict 2025-02-13 21:24:05 -06:00
abdulhakeem
1a0530fc2b Fix conflict during rebasing 2025-02-13 21:21:11 -06:00
Zafir Stojanovski
c64a32155a lint 2025-02-13 21:15:17 -06:00
Zafir Stojanovski
aaf1df285e string insertion 2025-02-13 21:15:17 -06:00
Andreas Koepf
0e8bf42ddd use json formatting for initial state of game-of-life board 2025-02-13 19:06:20 +01:00
Andreas Koepf
1996ffa6d8 add ProductsDataset (multiplication tasks) 2025-02-13 17:59:02 +01:00
Andreas Koepf (aider)
583ebfd5de feat: Add ProductsDataset with configurable terms and digits 2025-02-13 17:50:19 +01:00
Andreas Koepf
321b2a88e0 feat: Add PowerFunctionConfig and PowerFunctionDataset to arithmetic module exports 2025-02-13 17:50:17 +01:00
Andreas Köpf
db00818e76 Merge pull request #125 from open-thought/rich/gol2
Game of Life Output Formatting
2025-02-13 17:42:22 +01:00
Zafir Stojanovski
3202908c50 string synthesis 2025-02-13 16:33:28 +01:00
Rich Jones
9004e89bc3 Merge branch 'main' into rich/graphcolor 2025-02-13 13:43:34 +01:00
Rich Jones
b5df965d06 Merge branch 'main' into rich/graphcolor 2025-02-13 13:42:54 +01:00
Rich Jones
20b0b65093 address comments abt formatting 2025-02-13 13:42:34 +01:00
Rich Jones
55b75602ed json gol 2025-02-13 13:25:38 +01:00
Andreas Köpf
1a7d248607 Merge branch 'main' into env/string-insertion 2025-02-13 13:07:29 +01:00
Andreas Köpf
aeeba4e3f9 Merge pull request #119 from zafstojano/env/string-modification
String Manipulation
2025-02-13 13:03:42 +01:00
Andreas Koepf
07bb87d872 format answer in polynomial_equations to match expected format, add unit test 2025-02-13 12:09:20 +01:00
abdulhakeem
62a0d14355 Add useful instructions to question template of some datasets 2025-02-13 00:49:31 -06:00
Rich Jones
14052133bb add graph coloring 2025-02-13 01:28:09 +01:00
Zafir Stojanovski
b45d777e2c string manipulation 2025-02-12 22:28:23 +01:00
Zafir Stojanovski
4f11003ab7 lint 2025-02-12 17:26:23 +01:00
Andreas Koepf
c6a9dae0c6 use *args param for _define_attributes() 2025-02-12 16:59:09 +01:00
Zafir Stojanovski
4c5bc58a29 string insertion 2025-02-12 15:18:51 +01:00
Andreas Köpf
1669bba91b Merge branch 'main' into env/pool_matrix 2025-02-12 14:07:25 +01:00
Zafir Stojanovski
41556dd054 min matrix size, fixed question template 2025-02-12 11:20:55 +01:00
Zafir Stojanovski
52a56cbc4f system prompt for structured output, and parse such outputs 2025-02-12 10:44:42 +01:00
Andreas Koepf
6c5ee5b915 update GALLERY.md & bump version 2025-02-11 23:43:56 +01:00
Andreas Koepf (aider)
59461aaec8 fix: Add validation for size parameter in ABConfig 2025-02-11 23:39:57 +01:00
Andreas Köpf
18df4d33e8 Merge branch 'main' into rich/ab 2025-02-11 23:34:48 +01:00
Andreas Köpf
96558ddea5 Merge pull request #115 from zafstojano/env/count-primes
(env): Count primes in an interval
2025-02-11 23:19:03 +01:00