Commit graph

84 commits

Author SHA1 Message Date
Zafir Stojanovski
6cc5d0dd63 normalize answer and partial reward 2025-02-09 11:13:23 +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 Koepf
3ca9a709e8 gsm_symbolic generator changes 2025-02-05 20:58:01 +01:00
Andreas Koepf
94f877d17a use explicit rng for zebra generation (not yet fully deterministic) 2025-02-04 00:00:54 +01:00
Andreas Koepf
156b09951e black formatting 2025-02-03 22:57:24 +01:00
Adefioye
a80339a0e6 Merge branch 'main' into koko/gsm-symbolic-task-1 2025-02-03 01:23:26 -06:00
abdulhakeem
5e71fb2694 Refactor gsm symbolic dataset 2025-02-03 01:21:21 -06:00
Andreas Koepf
94eeff3255 post merge formatting 2025-02-02 15:24:39 +01:00
benjamrio
7acd4cb1e5 added calendar-arithmetic tasks 2025-02-02 14:54:32 +01:00
Andreas Koepf (aider)
2c979c3913 refactor: Use field default_factory TimeIntervalsConfig, AdvancedGeometryConfig 2025-02-02 09:55:51 +01:00
abdulhakeem
548b8fab15 Remove data 2025-02-01 20:31:44 -06:00
abdulhakeem
1e0dbc9875 Create python generator files for gsm symbolic templates 2025-02-01 20:23:30 -06:00
Andreas Koepf
90e448342f add pull-request: write permission for pre-commit checks 2025-02-01 02:36:20 +01:00
Andreas Koepf
44f32e3862 Add time interval dataset class 2025-02-01 02:10:48 +01:00
abdulhakeem
ff13dc6825 Still experimenting 2025-01-30 23:51:31 -06:00
Andreas Koepf
d90548658e fix chain_sum unit test 2025-01-30 10:57:55 +01:00
Andreas Koepf (aider)
a0c9c6b4fb test: Add comprehensive unit tests for QuantumLockDataset 2025-01-30 01:21:15 +01:00
Andreas Koepf
ad9f0d265c fix unit tests, lower python dependency to 3.9 2025-01-26 16:55:17 +01:00
Andreas Koepf
519e411fa5 add reasoning_gym.create_dataset({name}, ...) global factory function 2025-01-25 00:58:34 +01:00
Andreas Koepf
0d2d8ba6a0 pass config to ProceduralDataset base 2025-01-25 00:23:05 +01:00
Andreas Koepf (aider)
b3a2b719c7 feat: Register chain_sum dataset with register_dataset function 2025-01-25 00:01:41 +01:00
Andreas Koepf
5c5d46b4bd formatting, cleanup 2025-01-24 17:12:42 +01:00
Andreas Koepf
9d436af2b9 Add support for integer division in basic arithmetic dataset 2025-01-24 15:07:31 +01:00
Andreas Koepf (aider)
3ac07f6558 feat: Add support for integer division in BasicArithmeticDataset 2025-01-24 11:30:38 +01:00
Andreas Koepf (aider)
88fe366ef6 refactor: Simplify GCD number generation logic with break statement 2025-01-24 11:10:06 +01:00
Andreas Koepf (aider)
1bf62cbac2 refactor: Simplify LCM number generation with break and single return 2025-01-24 11:08:30 +01:00
Andreas Koepf
aaabc05ace formatting 2025-01-24 10:34:07 +01:00
Andreas Koepf
0e9250bce0 Rename ArithmeticDataset to BasicArithmeticDataset 2025-01-24 10:31:26 +01:00
Andreas Koepf (aider)
4817c33b65 refactor: Inherit LegCountingDataset from ProceduralDataset 2025-01-24 10:19:11 +01:00
Andreas Koepf
fef97fd2bb refactor: Simplify imports in leg_counting.py 2025-01-24 10:19:10 +01:00
Andreas Koepf (aider)
e4b032c814 refactor: Rename ArithmeticDataset to BasicArithmeticDataset 2025-01-24 10:02:02 +01:00
Andreas Koepf (aider)
339d515ecf refactor: Inherit ArithmeticDataset from ProceduralDataset base class 2025-01-24 10:00:19 +01:00
Andreas Koepf (aider)
4932b04106 refactor: Inherit PrimeFactorizationDataset from ProceduralDataset base class 2025-01-24 09:59:08 +01:00
Andreas Koepf (aider)
d1296630b4 refactor: Inherit ChainSum from ProceduralDataset base class 2025-01-24 09:57:26 +01:00
Andreas Koepf (aider)
e9e578a1df refactor: Inherit LCMDataset from ProceduralDataset base class 2025-01-24 09:56:19 +01:00
Andreas Koepf (aider)
89ad482b39 refactor: Inherit GCDDataset from ProceduralDataset base class 2025-01-24 09:55:14 +01:00
Andreas Koepf (aider)
c0552097c3 feat: Add ProceduralDataset abstract base class for dataset generators 2025-01-24 09:51:04 +01:00
Andreas Koepf
c0ca668ce9 refactor: Update fraction simplification config with expanded value ranges 2025-01-24 09:51:03 +01:00
Andreas Koepf (aider)
5fb6421179 refactor: Replace if/elif chain with match/case in _format_fraction 2025-01-24 09:43:13 +01:00
Andreas Koepf (aider)
0cb01efbc5 feat: Update fraction simplification config to use Sequence and default tuple for styles 2025-01-24 09:42:07 +01:00
Andreas Koepf (aider)
e282a779a9 feat: Add configurable formatting styles for fraction simplification dataset 2025-01-24 09:39:21 +01:00
Andreas Koepf (aider)
e1e59d2a2f feat: Ensure numerator is always smaller than denominator in fraction generation 2025-01-24 09:35:02 +01:00
Andreas Koepf (aider)
1cc3e434a0 refactor: Simplify fraction simplification dataset metadata 2025-01-24 09:30:12 +01:00
Andreas Koepf (aider)
0051d46466 feat: Add multiple LaTeX fraction formatting styles to FractionSimplificationDataset 2025-01-24 09:28:58 +01:00
Andreas Koepf
b29f81a4dc add gcd default max_value to 10_000 2025-01-24 09:18:46 +01:00
Andreas Koepf (aider)
b48307a9ec fix: Ensure simplified fraction values stay within configured bounds 2025-01-24 09:11:07 +01:00
Andreas Koepf (aider)
dce32139f3 feat: Add fraction simplification dataset to arithmetic module 2025-01-24 09:10:15 +01:00
Andreas Koepf (aider)
d8cce4672b feat: Modify LCM dataset to generate numbers with LCM less than their product 2025-01-24 09:02:57 +01:00
Andreas Koepf (aider)
830b1e3979 feat: Enhance GCD dataset to retry generating numbers with GCD > 1 2025-01-24 08:58:59 +01:00
Andreas Koepf (aider)
e58a0e2f94 feat: Add LCM dataset generator for arithmetic reasoning tasks 2025-01-24 08:55:16 +01:00