open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-04-23 16:55:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
858 commits 21 branches 5 tags 37 MiB
Commit graph

858 commits

This branch
This branch
All branches
Author SHA1 Message Date
Rich Jones
eb64e3a2b8 add random paren grouping 2025-02-20 10:46:01 +01:00
Rich Jones
a76e56fccc implement decimal precision 2025-02-19 12:30:07 +01:00
Rich Jones
0cd2eb50d7 Merge branch 'rich/decimalmath' of github.com:open-thought/reasoning-gym into rich/decimalmath 2025-02-19 03:34:57 +01:00
Rich Jones
c3bc7937dc [wip] more flexible api 2025-02-19 03:29:40 +01:00
Rich Jones
36b2bceda3 Merge branch 'main' into rich/decimalmath 2025-02-18 20:53:36 +01:00
Rich Jones
bd56a7b1fe lint 2025-02-18 19:22:03 +01:00
Rich Jones
e2bdfb4c1c decimal math 2025-02-18 19:20:33 +01:00
Andreas Köpf
aefcad9779 Merge pull request #73 from zafstojano/env/palindrome-partitioning 
Palindrome Partitioning
 2025-02-18 14:36:57 +01:00
Zafir Stojanovski
6b0ea7a14c lint 2025-02-18 14:24:07 +01:00
Zafir Stojanovski
fd5c47d634 update generation of input string 2025-02-18 14:23:05 +01:00
Zafir Stojanovski
ed606631bb Merge branch 'main' of https://github.com/open-thought/reasoning-gym into env/palindrome-partitioning 2025-02-18 14:08:00 +01:00
Andreas Köpf
f0572d550a Merge pull request #151 from olliestanley/feature/game-instructions 
Tweaks to prompt formats and scoring for some datasets
 2025-02-18 07:32:27 +01:00
Andreas Köpf
14c0daff59 Merge pull request #152 from open-thought/verl_basic_curriculum 
add grpo config for verl example
 2025-02-17 22:06:08 +01:00
Andreas Koepf
c40069e616 add grpo launch script 2025-02-17 20:52:03 +00:00
Oliver
49081e44bc Constrain reward 2025-02-17 19:20:45 +00:00
Oliver
0de0044d52 Formatting/scoring improvements for BF & family 2025-02-17 19:08:15 +00:00
Andreas Koepf
b1e07b7782 update config to latest veRL version 2025-02-17 18:43:51 +00:00
Oliver
b40c44059d Cleanup question & add scoring for mini sudoku 2025-02-17 18:37:07 +00:00
Andreas Köpf
54d52ef6ae Merge pull request #147 from Adefioye/koko/question-template-tinkering 
Tweaking some question templates
 2025-02-17 18:22:49 +01:00
Andreas Köpf
680665992f Merge pull request #150 from zafstojano/fix/rectangle-count 
fix(env): Rectangle Count
 2025-02-17 18:22:35 +01:00
Andreas Köpf
97a444040b Merge pull request #149 from zafstojano/fix/base-conversion 
fix(env): Base Conversion
 2025-02-17 18:21:39 +01:00
Andreas Koepf
aa794253fe minor formatting changes 2025-02-17 18:20:18 +01:00
Andreas Köpf
5654f300b9 Merge pull request #106 from tohskai/multivariate-polynomial-multiplication 
Better support for multivariate polynomials in PolynomialMultiplicationDataset
 2025-02-17 18:08:36 +01:00
abdulhakeem
d3323b1a77 Remove python code reference in count_primes prompt 2025-02-17 10:29:14 -06:00
tohskai
28fcf4d481 Refactor PolynomialMultiplicationDataset and fix issues with score_answer 2025-02-17 17:04:48 +01:00
Zafir Stojanovski
1c75f7cfd2 fix prompt 2025-02-17 16:12:50 +01:00
Zafir Stojanovski
38e8e371b6 fix prompt 2025-02-17 14:21:10 +01:00
Andreas Köpf
a80d5b1c55 Merge pull request #148 from zafstojano/fix/letter-jumble 
fix(env): Letter Jumble
 2025-02-17 13:29:02 +01:00
Zafir Stojanovski
c9895f1023 fix prompt and scoring function 2025-02-17 13:17:29 +01:00
abdulhakeem
ff8cd11a2d Fix unit test 2025-02-17 03:13:06 -06:00
abdulhakeem
5b1e42f878 Tweaked some question templates 2025-02-17 02:58:42 -06:00
Andreas Koepf
99b49f868f fix question templates 2025-02-16 23:04:24 +01:00
Andreas Köpf
79758a31de Merge pull request #105 from open-thought/circuit_logic 
initial draft for circuit_logic dataset generator
 2025-02-16 22:54:43 +01:00
Andreas Koepf
5348d9ed69 fix comment: legend no longer part of metadata 2025-02-16 22:53:18 +01:00
Andreas Koepf (aider)
0051c266d4 feat: Add scoring method & unit tests for circuit logic dataset 2025-02-16 22:48:51 +01:00
Andreas Köpf
2f3f2c7ccc Merge pull request #146 from zafstojano/fix/word-sorting 
fix(env): Word Sorting
 2025-02-16 21:55:52 +01:00
Andreas Köpf
6997c71a8b Merge pull request #145 from joesharratt1229/fix/games 
Fix/games
 2025-02-16 21:54:10 +01:00
Zafir Stojanovski
a27704b44e fix template 2025-02-16 19:51:24 +01:00
joesharratt1229
2c032a2500 restrcutured maze prompt template 2025-02-16 18:26:24 +00:00
joesharratt1229
94e07ddbf2 updated tower of hanoi question template 2025-02-16 17:54:33 +00:00
joesharratt1229
ca07c8584e updated countdown question template 2025-02-16 17:53:54 +00:00
joesharratt1229
cf6c15d0ee Merge pull request #144 from joesharratt1229/fix/arithmetic 
Added fixes for arithmetic environments
 2025-02-16 16:34:09 +00:00
joesharratt1229
230fffe0a4 formatted answer as str 2025-02-16 15:56:58 +00:00
Andreas Köpf
33f888dce7 Merge pull request #140 from theblackcat102/cryptarithm 
New task : Verbal arithmetic
 2025-02-16 16:41:44 +01:00
Andreas Köpf
7f42ec7b19 Merge pull request #143 from zafstojano/fix/string-synthesis 
fix(env): String Synthesis
 2025-02-16 16:39:30 +01:00
Andreas Koepf
b78408200c cryptarithm change defaults: size=500, include_example=True 2025-02-16 16:38:43 +01:00
Andreas Koepf
446913fee6 import CryptarithmDataset in algorithmic/__init__.py 2025-02-16 16:32:17 +01:00
Andreas Koepf
839c830c2a formatting 2025-02-16 16:30:28 +01:00
joesharratt1229
fff40f4f36 adjusted gsm symbolic question template 2025-02-16 15:28:44 +00:00
Andreas Koepf
6fae41a6e1 ensure reward is float 2025-02-16 16:27:12 +01:00