Commit graph

39 commits

Author SHA1 Message Date
Zafir Stojanovski
290bfc4fdd
(evals): Medium configs (#415)
* updated medium configs

* fix problematic curriculum values / small issues causing exceptions to be raised

* optimus alpha config

* all configs so far

* fix tests
2025-04-14 08:25:31 +02:00
Zafir Stojanovski
dced3bfc45
fix(curriculum): Make boundaries in curriculum more sensible (#407)
* init

* fix tests

* unify codeio

* filtered for libraries not present in reasoning-gym

* fix more bounds

* puzzle24

* knight swap curriculum

* fix number sorting

* fix attributes

* add validation of config in creation of dataset

* dry run for instantiating and validating the datasets

* remove unused imports

* fix curriculum tests to reference newly updated attribute names
2025-04-04 20:24:14 +02:00
Oliver Stanley
415bcb5ace
use constant for dataset name in arc agi (#404) 2025-04-01 22:06:31 +02:00
Adefioye
e3af2dd2bd
Add curriculum for arc_agi (#372)
* Add curriculum for arc_agi

* Resolve conflicts

* Remove code smell

* Remove unwanted code
2025-04-01 21:17:52 +02:00
Zafir Stojanovski
50846c3534
fix(env): ARC 1D curriculum (#402)
* Add arc_1d curriculum

* Add difficulty to metadata

* use range attribute instead of scalar

---------

Co-authored-by: abdulhakeem <abdulhakeemadefioye@gmail.com>
Co-authored-by: Oliver Stanley <olivergestanley@gmail.com>
2025-04-01 13:01:15 +02:00
Zafir Stojanovski
ce0a6c4878
fix(envs): Add source dataset and index to metadata (#388)
* add source dataset and index to metadata

* fix typo

* fix coach class and its test
2025-03-20 11:12:14 +00:00
Oliver Stanley
7475a20700
include ranges rather than sampled values in difficulty metadata dicts (#387)
* update difficulty metadata for logic datasets

* update difficulty metadata for graph datasets

* update difficulty metadata for geometry datasets

* update difficulty metadata for games datasets

* update difficulty metadata for cognition datasets

* update difficulty metadata for arithmetic datasets

* update difficulty metadata for arc datasets

* update difficulty metadata for algorithmic datasets

* update difficulty metadata for algebra datasets

* use tuples

* update tests

* update tests
2025-03-20 10:27:03 +01:00
Andreas Köpf
d2c895f1d3
Refactor Curriculum Attributes (#335)
* remove min_value from AttributeDefinition
* remove type from AttributeDefinition
* Add CurriculumContext
* add ensure_interval option for RangeAttributes
* docs: Add legend explaining curriculum indicators in dataset gallery
* update GALLERY.md
2025-03-16 15:40:28 +01:00
joesharratt1229
6354ca5d35
added rearc curr (#358) 2025-03-13 21:14:03 +01:00
Andreas Köpf
5d7fbac0ad
Minor question template & score_answer improvements (#261)
* math prompt improvements
* ignore brackets in complex_arithmetic results
* improve additional instruction in prompt of polynomial_equations
* more strict tests for score_answer in polynomial_equations
* simplify special reward handling
* fix test_intermediate_integration
* fix sokoban dataset
* add common dataset score_answer consistency test
2025-03-04 21:55:09 +01:00
Andreas Koepf
b1c8840129 fix prompt for arc_1d 2025-02-28 08:07:59 +01:00
Andreas Koepf
469934d9b7 minor arc_1d tweaks 2025-02-23 16:37:40 +01:00
Andreas Koepf
ec3050a4f6 remove unnecessary checks, use tuples 2025-02-23 13:17:48 +01:00
Andreas Koepf
7a45b14a49 fix index out of range of arc_1d dataset (#190) 2025-02-23 12:51:41 +01:00
Andreas Koepf
eeb9fa31d5 more native type hints 2025-02-21 21:23:14 +01:00
Andreas Koepf
3e7ff3b084 use native types List->list, Dict->dict, Set->set, Tuple->tuple 2025-02-21 15:15:38 +01:00
Andreas Koepf
52b1fd1cae add configuration option for ArcAgiDataset 2025-02-16 12:49:21 +01:00
Andreas Koepf
5410bb78a0 add ProductsDataset (multiplication tasks) 2025-02-13 17:59:02 +01:00
Andreas Koepf (aider)
3137e0f433 feat: Add configurable rotation and mirror augmentation variants 2025-02-09 00:16:41 +01:00
Andreas Koepf
40f418bfb9 refactor: Reorganize ArcAgiConfig class attributes for better readability 2025-02-09 00:12:59 +01:00
Andreas Koepf
39b5599f40 formatting 2025-02-09 00:04:42 +01:00
Andreas Koepf (aider)
e8e918c9de fix: Add missing Callable import to arc_agi.py 2025-02-08 23:59:53 +01:00
Andreas Koepf (aider)
f8e76b8048 feat: Add configurable augmentations to ArcAgiDataset with consistent application 2025-02-08 23:59:45 +01:00
Andreas Koepf
492570ff5c add rotate, mirror & color-mapping augmentation functions 2025-02-08 23:51:38 +01:00
Andreas Koepf
127f505798 add ArcAgiDataset class, fix score_entry() metadata params 2025-02-08 23:18:18 +01:00
Andreas Koepf
60effc6e7a move arc_1d into from cognition into arc folder 2025-02-08 19:37:26 +01:00
Andreas Koepf
63cbb8722d remove unnecessary newline from arc prompt 2025-02-08 19:12:41 +01:00
Andreas Koepf
d0ee809757 re-arc cleanup 2025-02-08 19:07:28 +01:00
joesharratt1229
4023efd311 added lne length constraint to ea32f347 task 2025-02-08 11:42:49 +00:00
joesharratt1229
a1494c4e5b adapted score answer 2025-02-08 11:42:49 +00:00
joesharratt1229
ab33c2bcbb added parse func 2025-02-08 11:42:49 +00:00
joesharratt1229
65b61912ba fixed rng err 2025-02-08 11:42:49 +00:00
joesharratt1229
4d9ea46c85 added validation 2025-02-08 11:42:49 +00:00
joesharratt1229
4c94975d15 added generator directory 2025-02-08 11:42:49 +00:00
joesharratt1229
b28283a31b added rearc score answer and visualisation methods 2025-02-08 11:42:49 +00:00
joesharratt1229
4f74d73994 added rearc board format 2025-02-08 11:42:49 +00:00
joesharratt1229
f10236a64c fixed relative imports 2025-02-08 11:42:49 +00:00
joesharratt1229
184d5b4270 registered rearc 2025-02-08 11:42:49 +00:00
joesharratt1229
e836add270 added rearc impl 2025-02-08 11:42:40 +00:00