open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-04-19 12:58:07 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
701 commits 21 branches 5 tags 37 MiB
Commit graph

97 commits

Author SHA1 Message Date
Andreas Koepf
5410bb78a0 add ProductsDataset (multiplication tasks) 2025-02-13 17:59:02 +01:00
Andreas Koepf (aider)
bdcaeff42a feat: Add ProductsDataset with configurable terms and digits 2025-02-13 17:50:19 +01:00
Andreas Koepf
3ead141db5 feat: Add PowerFunctionConfig and PowerFunctionDataset to arithmetic module exports 2025-02-13 17:50:17 +01:00
Andreas Koepf
ab9f781d97 use *args param for _define_attributes() 2025-02-12 16:59:09 +01:00
Andreas Köpf
411a1789b1
Merge pull request #110 from open-thought/rich/dice 
Adds Dice Probability Dataset
 2025-02-11 22:54:02 +01:00
Andreas Köpf
3f8380d93a
Merge pull request #99 from open-thought/curriculum_basics 
Add foundation for auto-curriculum
 2025-02-11 22:52:14 +01:00
Rich Jones
0a4799d99a clarity 2025-02-11 16:22:53 +01:00
Rich Jones
945207da43 fmt 2025-02-11 12:54:23 +01:00
Rich Jones
852ddfcea3 add dice dataset 2025-02-11 12:53:13 +01:00
Andreas Koepf
4abcd1f1df update gallery, lower default config values for PowerFunctionDataset 2025-02-10 22:42:04 +01:00
Zafir Stojanovski
ed10111834
count bits (#101) 2025-02-10 22:12:50 +01:00
Zafir Stojanovski
a8c39ddcfb
Power Function (#102) 
* power function dataset + tests
 2025-02-10 22:04:58 +01:00
Andreas Koepf
8772041afb Add attributes for curriculum 
Co-authored-by: EduardDurech <39579228+EduardDurech@users.noreply.github.com>
 2025-02-10 18:58:07 +01:00
Zafir Stojanovski
ef2a412c8b normalize answer and partial reward 2025-02-09 11:13:23 +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
afb95508ef gsm_symbolic generator changes 2025-02-05 20:58:01 +01:00
Andreas Koepf
04cd81dd76 use explicit rng for zebra generation (not yet fully deterministic) 2025-02-04 00:00:54 +01:00
Andreas Koepf
c8fcb6ca02 black formatting 2025-02-03 22:57:24 +01:00
Adefioye
40b5c5583c
Merge branch 'main' into koko/gsm-symbolic-task-1 2025-02-03 01:23:26 -06:00
abdulhakeem
f2b5e88390 Refactor gsm symbolic dataset 2025-02-03 01:21:21 -06:00
Andreas Koepf
8b0f634f4c post merge formatting 2025-02-02 15:24:39 +01:00
benjamrio
943651c15b added calendar-arithmetic tasks 2025-02-02 14:54:32 +01:00
Andreas Koepf (aider)
4e9fc4baad refactor: Use field default_factory TimeIntervalsConfig, AdvancedGeometryConfig 2025-02-02 09:55:51 +01:00
abdulhakeem
01d8bc3175 Remove data 2025-02-01 20:31:44 -06:00
abdulhakeem
810beec935 Create python generator files for gsm symbolic templates 2025-02-01 20:23:30 -06:00
Andreas Koepf
0f6f58cae2 add pull-request: write permission for pre-commit checks 2025-02-01 02:36:20 +01:00
Andreas Koepf
7eb1466340 Add time interval dataset class 2025-02-01 02:10:48 +01:00
abdulhakeem
b203353751 Still experimenting 2025-01-30 23:51:31 -06:00
Andreas Koepf
5b35ea51a7 fix chain_sum unit test 2025-01-30 10:57:55 +01:00
Andreas Koepf (aider)
9480c18e16 test: Add comprehensive unit tests for QuantumLockDataset 2025-01-30 01:21:15 +01:00
Andreas Koepf
ecbb155184 fix unit tests, lower python dependency to 3.9 2025-01-26 16:55:17 +01:00
Andreas Koepf
0dcff77b37 add reasoning_gym.create_dataset({name}, ...) global factory function 2025-01-25 00:58:34 +01:00
Andreas Koepf
e9549f2a63 pass config to ProceduralDataset base 2025-01-25 00:23:05 +01:00
Andreas Koepf (aider)
df2b8d2809 feat: Register chain_sum dataset with register_dataset function 2025-01-25 00:01:41 +01:00
Andreas Koepf
3dc80be7d2 formatting, cleanup 2025-01-24 17:12:42 +01:00
Andreas Koepf
ddc22868e9 Add support for integer division in basic arithmetic dataset 2025-01-24 15:07:31 +01:00
Andreas Koepf (aider)
7a64273f2e feat: Add support for integer division in BasicArithmeticDataset 2025-01-24 11:30:38 +01:00
Andreas Koepf (aider)
d283177045 refactor: Simplify GCD number generation logic with break statement 2025-01-24 11:10:06 +01:00
Andreas Koepf (aider)
71b13cda07 refactor: Simplify LCM number generation with break and single return 2025-01-24 11:08:30 +01:00
Andreas Koepf
20069b2a7d formatting 2025-01-24 10:34:07 +01:00
Andreas Koepf
98988c8481 Rename ArithmeticDataset to BasicArithmeticDataset 2025-01-24 10:31:26 +01:00
Andreas Koepf (aider)
44fd0d4a25 refactor: Inherit LegCountingDataset from ProceduralDataset 2025-01-24 10:19:11 +01:00
Andreas Koepf
1f93058834 refactor: Simplify imports in leg_counting.py 2025-01-24 10:19:10 +01:00
Andreas Koepf (aider)
95d9974911 refactor: Rename ArithmeticDataset to BasicArithmeticDataset 2025-01-24 10:02:02 +01:00
Andreas Koepf (aider)
1b556b70f7 refactor: Inherit ArithmeticDataset from ProceduralDataset base class 2025-01-24 10:00:19 +01:00
Andreas Koepf (aider)
ad69954b6e refactor: Inherit PrimeFactorizationDataset from ProceduralDataset base class 2025-01-24 09:59:08 +01:00
Andreas Koepf (aider)
d191e78a28 refactor: Inherit ChainSum from ProceduralDataset base class 2025-01-24 09:57:26 +01:00
Andreas Koepf (aider)
0dc19b831c refactor: Inherit LCMDataset from ProceduralDataset base class 2025-01-24 09:56:19 +01:00
Andreas Koepf (aider)
c3170fd5f1 refactor: Inherit GCDDataset from ProceduralDataset base class 2025-01-24 09:55:14 +01:00
Andreas Koepf (aider)
018bdcef6f feat: Add ProceduralDataset abstract base class for dataset generators 2025-01-24 09:51:04 +01:00