Zafir Stojanovski
a969d8ef05
feat(curriculum): Knights and Knaves configs ( #488 )
...
* configs
* reduce complexity of curriculum
* update lower bound
* add failure threshold
* update last_k
* update thresholds for success and failure
* update curriculum file as well
* update run name for noncurriculum
* lint
* dtype model eval
* return binary scoring
* set eval repeats to 3
* fix tests
2025-07-31 10:18:05 +02:00
Oliver Stanley
1a727ecf4e
support python 3.10 ( #450 )
...
* support python 3.10
* add 3.10 to tests
* new StrEnum
2025-06-04 10:34:01 +01:00
Oliver Stanley
224532f12a
first inter-domain generalisation experiments ( #412 )
...
* tweak len reward
* first inter-generalisation experiment config
* update inter algorithmic config
* default to empty config
* fix typo
* change config to match experiment script
* long prompt fixes
* algorithmic training config tweaks
* imports
* update algorithmic training cfgs
* first logic composite config
* fix dset name
* tweaks
* fix syllogisms dataset
* rm temp print
* initial algebra config
* algebra cfg tweaks
* add gc
* add initial games cfg
* rename games cfg
* fix dset name
* fix sokoban metadata
* remove boxnet
* games cfg tweak
2025-04-14 21:06:40 +01:00
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
vncntt
cd85c2d632
add knights knaves curriculum ( #401 )
...
* add knights knaves curriculum
* add metadata + width constraints
2025-04-01 12:20:58 +02:00
Tiago Serafim
7ae2942c34
Fix small bit of old code ( #386 )
...
Removed the `sat_utils.` that was left there from the original zebra package.
This allows the zebra generator to be used with the full set of available clues.
2025-03-24 09:00:28 +00:00
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
Zafir Stojanovski
f72ecaf411
circuit logic curriculum ( #368 )
2025-03-14 16:17:00 +01:00
Zafir Stojanovski
d33c667c3d
feat(env): Propositional Logic Curriculum ( #365 )
...
* propositional logic curriculum
* lint
* difficulty meta
2025-03-14 16:12:39 +01:00
joesharratt1229
d603d8b72b
added aiw curric ( #356 )
...
added metadata
2025-03-13 21:10:52 +01:00
joesharratt1229
b497e35fb8
added self reference curr ( #329 )
2025-03-11 00:23:26 +01:00
joesharratt1229
54074b17ef
Added zebra curriculum ( #328 )
...
* added zebra curriculum
* added metadata
2025-03-11 00:22:54 +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
Zafir Stojanovski
01e1c8f9af
fix: Unify Prompts ( #254 )
...
* remove cot
* fix prompt template
* fix pool matrix
* spiral matrix fixed
2025-03-03 21:55:53 +01:00
vncntt
3149edf2c4
fixed problems in knights_knaves ( #251 )
...
* remove unnecessary variables
* added depth logic
* add depth tests
2025-03-02 08:47:54 +01:00
vncntt
5f01049607
Add KnightsKnavesDataset (knights_knaves)
...
Adapted code from https://github.com/AlphaPav/mem-kk-logic/blob/main/data_prep/lib_kk.py
---------
Co-authored-by: Andreas Koepf (aider) <andreas.koepf@provisio.com>
2025-02-25 20:15:38 +01:00
Andreas Koepf
7f30e711e5
reactivate default imports for PropositionalLogicDataset
2025-02-21 15:41:04 +01:00
Andreas Köpf
802b8c4bed
Merge branch 'main' into fix/prop_logix
2025-02-21 15:38:29 +01:00
Andreas Koepf
3e7ff3b084
use native types List->list, Dict->dict, Set->set, Tuple->tuple
2025-02-21 15:15:38 +01:00
joesharratt1229
5fb655e390
moved trivial check
2025-02-21 00:20:00 +00:00
joesharratt1229
39ee099a86
reimplemented prop logic
2025-02-20 23:59:31 +00:00
Andreas Koepf
147088051d
exclude PropositionalLogicDataset from auto-import (needs to be improved)
2025-02-20 12:08:48 +01:00
joesharratt1229
831822e899
added zebra
2025-02-19 18:13:03 +00:00
Andreas Koepf
2cbaab2918
fix question templates
2025-02-16 23:04:24 +01:00
Andreas Köpf
72fcb36cb4
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
3335df8ad4
fix comment: legend no longer part of metadata
2025-02-16 22:53:18 +01:00
Andreas Koepf (aider)
63bd662acf
feat: Add scoring method & unit tests for circuit logic dataset
2025-02-16 22:48:51 +01:00
joesharratt1229
d0200d1dbe
formatted answer as str
2025-02-16 15:56:58 +00:00
Dragan Jovanović
719369bce6
fix for isort
2025-02-11 00:20:46 +01:00
Dragan Jovanović
60d0785a91
initial draft for circuit_logic dataset generator
2025-02-11 00:09:00 +01:00
Andreas Koepf
0c3b2c4fef
lint
2025-02-08 17:22:55 +01:00
Andreas Koepf (aider)
ac27508d09
feat: Add inversion probability and logical equivalence to syllogisms
2025-02-08 17:14:35 +01:00
Andreas Köpf
0c8752c7b1
Fix syllogisms ( #82 )
...
* let o1 write a new is_valid_syllogism() check
* extend unit test
* update gallery
2025-02-07 21:47:59 +01:00
Andreas Koepf
d3752a0d76
bump version to 0.1.14
2025-02-07 18:28:06 +01:00
Rich Jones
bd8fc9beeb
add self-reference puzzles
2025-02-07 15:09:42 +01:00
Andreas Köpf
3f6b2fc807
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 Koepf
cd3c95baf0
update notice of 3rd party code import
2025-02-04 13:47:57 +01:00
Andreas Koepf
9bc92952f8
minimize changes
2025-02-04 11:46:19 +01:00
Andreas Koepf
f2b4c3d078
use sorted() and OrderedDict to make zebra puzzle clue order deterministic
2025-02-04 11:24:04 +01:00
Andreas Koepf
f5128207a6
minor logic puzzle changes
2025-02-04 00:18:21 +01:00
Andreas Koepf
2b6315474a
remove solver graph folder
2025-02-04 00:07:01 +01:00
Andreas Koepf
04cd81dd76
use explicit rng for zebra generation (not yet fully deterministic)
2025-02-04 00:00:54 +01:00
Rich Jones
4d950e562a
cleanup
2025-02-03 16:47:29 +01:00
Rich Jones
7274f79c50
precommit hook linting
2025-02-03 14:40:58 +01:00
Rich Jones
0c9094e9f4
adds zebrapuzzles
2025-02-03 14:34:57 +01:00
Andreas Koepf (aider)
56ded2c299
feat: Improve syllogism sentence formatting for natural language
2025-02-02 17:23:02 +01:00
Andreas Koepf
f396d3df60
post merge lint
2025-02-02 10:04:18 +01:00
rishabhranawat
5f6d615369
[aiw] remove output format template
2025-02-01 16:33:08 -08:00
