Zafir Stojanovski
8d4e9030c0
manipulate matrix curriculum ( #293 )
2025-03-08 01:57:37 +01:00
Zafir Stojanovski
e69ed78c26
feat(env): Isomorphic Strings Curriculum ( #292 )
...
* isomorphic strings curriculum
---------
Co-authored-by: Andreas Köpf <andreas.koepf@xamla.com>
2025-03-08 01:56:14 +01:00
joesharratt1229
af5a6533c8
added word sort curriculum ( #289 )
2025-03-08 01:50:13 +01:00
Zafir Stojanovski
2d05a48f9b
feat(env): Group Anagrams Curriculum ( #288 )
...
* group anagrams curriculum
2025-03-08 01:49:12 +01:00
Zafir Stojanovski
9fc9cf4597
feat(env): Count Primes Curriculum ( #287 )
...
* count primes curriculum
2025-03-08 01:48:00 +01:00
Zafir Stojanovski
adf8cd8f6d
base conversion curriculum ( #286 )
2025-03-08 01:46:32 +01:00
Zafir Stojanovski
25b8e35589
feat(env): Binary Matrix Curriculum ( #279 )
...
* binary matrix curriculum
* register BinaryMatrixCurriculum
---------
Co-authored-by: Andreas Koepf <andreas.koepf@provisio.com>
2025-03-07 22:58:47 +01:00
Zafir Stojanovski
a8e920b552
feat(env): Binary Alternation Curriculum ( #278 )
...
* binary alternation
---------
Co-authored-by: Andreas Koepf <andreas.koepf@provisio.com>
2025-03-07 22:44:32 +01:00
Andreas Koepf
c504efc2c3
use relative import for reasoning_gym.data
2025-03-07 15:56:45 +01:00
Rich Jones
07dc01ad87
[Env] Game of Life Halting Prediction ( #272 )
...
This is a variant of the Game of Life task, which rather than trying to test the algorithmic simulation, tests the ability of the model to do explanatory reasoning of the board. The idea is that a model with good explanatory reasoning will be able to see that a game will not halt without simulating it into the future.
The task presents a GoL board, and the model is asked to predict if the board will halt (die, all cells zero) after n steps. Sometimes, the board will be made up of 'oscillators', isolated structures which never die. Othertimes, it is filled with non-oscillators, structures which will always die after a few steps. The model should deduce which case the presented board is.
2025-03-07 10:05:12 +01:00
joesharratt1229
d9638df79c
updated algorithmics dataset ( #269 )
...
* updated algorithmic datasets
* added changes to symbolic and power
* updated power function test
2025-03-05 23:32:53 +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
Rich Jones
0ba6119850
Game of Life partial scoring and rule-clarification ( #258 )
...
* partial scoring and rule clarification
* better ql scoring
* word seq reverse typos
2025-03-03 22:22:39 +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
joesharratt1229
49db4ed761
small change to word sequence reversal prompt ( #252 )
...
corrected ansewr format
2025-03-02 17:34:35 +01:00
Zafir Stojanovski
f549909c3d
fix manipulate matrix ( #247 )
2025-03-01 23:00:29 +01:00
Rich Jones
39f151ad14
more dynamic scoring for jumble ( #246 )
2025-03-01 18:50:59 +01:00
Rich Jones
a6c90f40a1
rm typo
2025-02-27 13:44:33 +01:00
Rich Jones
1b95cd3206
fix graph color example template
2025-02-27 13:43:01 +01:00
AhmedSaif2
dcdc38b15d
Fix primes representation in count_primes dataset metadata
2025-02-26 14:58:21 +02:00
Andreas Köpf
48f082663a
Fix PoolMatrixConfigs::score_answer(), add unit tests ( #215 )
2025-02-26 00:43:18 +01:00
Andreas Koepf
bba128ffd0
fix score_answer of pool_matrix (if -> elif), remove print
2025-02-25 23:43:29 +01:00
Andreas Koepf
f9e8f8b064
add try-except to GraphColorDataset.score_answer()
2025-02-25 23:43:29 +01:00
Andreas Koepf
65d17b9850
add None/empty check to score_answer of cryptarithm
2025-02-25 23:43:29 +01:00
Andreas Koepf
eeb9fa31d5
more native type hints
2025-02-21 21:23:14 +01:00
Andreas Köpf
2947038557
Merge pull request #182 from zafstojano/env/binary-alternation
...
feat(env): Binary Alternation
2025-02-21 17:27:16 +01:00
Andreas Köpf
a6a5d30f1c
Merge pull request #175 from AhmedSaif2/fix-format
...
Add score_answer function to handle comma-formatted numbers
2025-02-21 15:36:21 +01:00
Andreas Koepf
3e7ff3b084
use native types List->list, Dict->dict, Set->set, Tuple->tuple
2025-02-21 15:15:38 +01:00
Zafir Stojanovski
96464388bb
pre-commit
2025-02-21 13:39:05 +01:00
Zafir Stojanovski
941085e0c5
binary alternation
2025-02-21 13:09:21 +01:00
Andreas Köpf
000e179781
Merge branch 'main' into env/rotten-oranges
2025-02-20 22:51:07 +01:00
Andreas Koepf
c236bcf1b6
store possible answer in entry 'answer' field
2025-02-20 22:47:21 +01:00
Andreas Koepf (aider)
9068e1d1b1
docs: Add descriptive comments for num_jugs and difficulty parameters
2025-02-20 22:39:22 +01:00
Andreas Koepf (aider)
ece040a0d0
feat: Add type hints to generate_puzzle and min_moves_n functions
2025-02-20 22:38:11 +01:00
Andreas Koepf
d7db2ed838
refactor: Simplify jug puzzle dataset generation and solution verification
2025-02-20 22:38:10 +01:00
Zafir Stojanovski
8709ec1ca3
remove empty space
2025-02-20 22:35:53 +01:00
Zafir Stojanovski
0d65bf3668
rotten oranges
2025-02-20 22:33:39 +01:00
Rich Jones
0f798457ed
jugs jugs jugs lint
2025-02-20 16:15:29 +01:00
Rich Jones
6f00690ae1
basic jugs
2025-02-20 15:24:46 +01:00
Andreas Köpf
e25973b118
Merge pull request #158 from open-thought/rich/decimalmath
...
Decimal Arithmetic
2025-02-20 12:35:41 +01:00
Andreas Koepf
50eab616f8
use correct signature for CryptarithmDataset.score_answer() method
2025-02-20 11:55:32 +01:00
Andreas Köpf
6bbe8886e5
Merge pull request #155 from theblackcat102/cryptarithm
...
Cryptarithm add score_answer function
2025-02-20 11:28:03 +01:00
Rich Jones
445b63bbf2
fix weird GoL fmt
2025-02-20 11:09:29 +01:00
theblackcat102
44559aac95
[fix] precommit not happy
2025-02-20 17:00:18 +08:00
theblackcat102
407b212326
[feat] remove answer parsing since its already handled
2025-02-20 16:57:51 +08:00
joesharratt1229
9a5ed19eba
cleaned up caesar cipher
2025-02-19 18:11:59 +00:00
theblackcat102
9a2e9e949e
[fix] normalize to <answer></answer>
2025-02-19 08:40:31 +08:00
theblackcat102
bbc31e4291
[fix] pre-commit fix
2025-02-18 21:48:54 +08:00
theblackcat102
c612e2abc1
[feat] add test case
2025-02-18 21:45:51 +08:00
theblackcat102
f27746be17
Merge remote-tracking branch 'upstream/main' into cryptarithm
2025-02-18 21:34:42 +08:00
