Aayam
fa102721f2
pre commit run changes
2025-02-07 07:42:03 -08:00
Aayam
cf25ca94b9
All number are integers now.
2025-02-07 07:34:17 -08:00
Aayam
d675ea843e
Apply pre-commit fixes
2025-02-07 07:01:20 -08:00
Aayam
50b96bff73
added explicit check for answer to metadata result match
2025-02-07 07:01:20 -08:00
Andreas Köpf
c3ba476b72
Merge pull request #78 from JeanKaddour/main
...
Feat: Add Tsumego
2025-02-07 14:10:29 +01:00
tohskai
998d142d9f
Add PolynomialMultiplicationDataset ( #64 )
...
* Add PolynomialMultiplicationDataset
2025-02-07 14:06:41 +01:00
Jean Kaddour
741118eb52
feat: add tsumego
2025-02-07 11:22:33 +00:00
Andreas Köpf
1b49713116
Sokoban without pygame ( #77 )
...
* add minified version of https://github.com/xbandrade/sokoban-solver-generator
---------
Co-authored-by: Rich Jones <miserlou@gmail.com>
2025-02-07 11:57:53 +01:00
Andreas Köpf
a8f9eafd43
docs: Update TRL README with GRPO example details and usage instructions ( #76 )
2025-02-07 07:56:22 +01:00
joesharratt1229
d61db3772a
Test training with trl ( #70 )
...
* first trl grpo implementation
* added config yaml file
* added read me and dependencies
* updated reward format func
2025-02-07 07:42:32 +01:00
Andreas Köpf
a607db79f7
Add Coaching & ScoreBoard class (result tracking) ( #72 )
...
* feat: Add Coach and ScoreBoard classes for performance tracking and difficulty adjustment
* feat: Add GroupedScores class to wrap aggregated scores
* refactor: Create ScoreStats class with tuple-based score statistics
* feat: Add unit test for Coach with CompositeDataset and multiple datasets
* fix: Add difficulty metadata to leg counting dataset
* feat: Add clear() method to ScoreBoard to reset all stored data
* feat: Add __len__ method to ScoreBoard to return number of scores
* feat: Add update_dataset_config method to CompositeDataset
* cleanup __init__ & imports
2025-02-06 23:15:28 +01:00
Andreas Köpf
05e2681ada
Merge pull request #75 from zafstojano/chore/remove-unused-methods
...
chore(envs): Remove unmodified dunder methods
2025-02-06 23:12:43 +01:00
Zafir Stojanovski
2dd53241e5
remove unmodified dunder methods
2025-02-06 22:56:11 +01:00
Andreas Koepf
b90c50e68f
remove redundant methods from GroupAnagramsDataset
2025-02-06 14:21:03 +01:00
Andreas Köpf
b23d25c92a
Merge pull request #65 from zafstojano/env/group-anagrams
...
Group Anagrams together
2025-02-06 13:03:27 +01:00
Zafir Stojanovski
40aed7fdd6
test malformed json answer
2025-02-06 10:13:02 +01:00
Zafir Stojanovski
cce890e169
use get_data_file_path to read file contents
2025-02-06 10:12:51 +01:00
Zafir Stojanovski
df8a7893dc
add source for words_alpha.txt
2025-02-06 10:12:38 +01:00
Zafir Stojanovski
7bec310591
delete words_alpha.txt
2025-02-06 10:12:25 +01:00
Andreas Köpf
14a600ee40
Merge pull request #68 from open-thought/revert-67-add-complex-number-arithmetic
...
Revert "feat: Add Complex Arithmetic Dataset and Tests"
2025-02-06 08:16:02 +01:00
Andreas Koepf
1df765e9e9
Revert "update GALLERY.md (complex_arithmetic)"
...
This reverts commit ff67fc8a51
2025-02-06 08:14:17 +01:00
Andreas Köpf
3f0fa88a89
Revert "feat: Add Complex Arithmetic Dataset and Tests"
2025-02-06 08:12:52 +01:00
Andreas Koepf
ff67fc8a51
update GALLERY.md (complex_arithmetic)
2025-02-06 08:00:40 +01:00
Andreas Köpf
b0922c9de3
Merge pull request #67 from idigitopia/add-complex-number-arithmetic
...
feat: Add Complex Arithmetic Dataset and Tests
2025-02-06 07:59:11 +01:00
Aayam
d49c042e64
Apply pre-commit fixes
2025-02-05 22:53:36 -08:00
Andreas Koepf
ac7180d757
move workflow permissions to job level
2025-02-06 07:26:50 +01:00
Zafir Stojanovski
dc6f6a4e7e
docs
2025-02-06 00:12:58 +01:00
Zafir Stojanovski
7f611c2e0e
group anagrams env
2025-02-06 00:11:07 +01:00
Andreas Koepf
bb618d4b87
update dataset gallery
2025-02-05 21:17:37 +01:00
Andreas Köpf
2641033c4c
Merge pull request #63 from open-thought/gsm_symbolic_tests
...
Gsm symbolic fixes
2025-02-05 21:15:35 +01:00
Andreas Koepf
1e7864eb2a
update gsmcross-check status
2025-02-05 21:14:19 +01:00
Andreas Koepf
3ca9a709e8
gsm_symbolic generator changes
2025-02-05 20:58:01 +01:00
Andreas Köpf
03c57ff569
Merge pull request #61 from open-thought/composite_dataset
...
Add composite dataset
2025-02-05 19:05:31 +01:00
Aayam
a0e291d066
feat: Add Complex Arithmetic Dataset and Tests
...
This commit introduces a new dataset for complex number arithmetic operations:
- Implements ComplexArithmeticDataset for generating complex number problems
- Supports addition, subtraction, multiplication, and division operations
Part of the algebra tasks collection in reasoning-gym.
2025-02-05 08:53:06 -08:00
Zafir Stojanovski
74471ac85c
generate all english anagrams
2025-02-05 16:25:23 +01:00
Andreas Köpf
00b81fa4dc
Merge pull request #62 from zafstojano/env/course-schedule
...
Course Schedule (Topological Sort)
2025-02-05 14:18:37 +01:00
Zafir Stojanovski
0b8fb1f6aa
typo
2025-02-05 12:08:18 +01:00
Zafir Stojanovski
0de4d5ca4c
course schedule
2025-02-04 23:50:24 +01:00
Andreas Koepf
3e28a14d54
register composite dataset
2025-02-04 19:17:34 +01:00
Andreas Koepf (aider)
6ec8f782d7
feat: Add pyyaml dependency to project configuration
2025-02-04 19:07:52 +01:00
Andreas Koepf (aider)
0b7c1344a1
fix: Correct indentation and implementation of create_dataset function
2025-02-04 19:06:41 +01:00
Andreas Koepf (aider)
d1050742fc
fix: Move dataset registration after function definition to resolve undefined name error
2025-02-04 19:06:24 +01:00
Andreas Koepf (aider)
f07b6b7f61
Based on the implementation and requirements, here's a concise commit message:
...
feat: Add CompositeDataset for weighted multi-dataset sampling
2025-02-04 19:06:13 +01:00
Andreas Koepf
0561844779
update notice of 3rd party code import
2025-02-04 13:47:57 +01:00
Andreas Koepf
00b693570b
use PYTHONHASHSEED=1 for generate_gallery.py
2025-02-04 12:03:45 +01:00
Andreas Köpf
8eb3145468
Merge pull request #59 from open-thought/fix_zebra_order
...
Make zebra puzzle clue order deterministic
2025-02-04 11:48:52 +01:00
Andreas Koepf
b07f91277d
minimize changes
2025-02-04 11:46:19 +01:00
Andreas Koepf
1142d9e6be
use sorted() and OrderedDict to make zebra puzzle clue order deterministic
2025-02-04 11:24:04 +01:00
Andreas Köpf
4a78b028f0
Merge pull request #57 from zafstojano/env/largest-island
...
Find Largest Island (BFS)
2025-02-04 00:20:06 +01:00
Andreas Koepf
7e5c427aea
minor logic puzzle changes
2025-02-04 00:18:21 +01:00
