base conversion curriculum (#286)

reasoning_gym/algorithmic/__init__.py

@@ -7,7 +7,7 @@ Algorithmic tasks for training reasoning capabilities:
 """
 
 from .ab import ABConfig, ABDataset
-from .base_conversion import BaseConversionConfig, BaseConversionDataset
+from .base_conversion import BaseConversionConfig, BaseConversionCurriculum, BaseConversionDataset
 from .binary_alternation import BinaryAlternationConfig, BinaryAlternationCurriculum, BinaryAlternationDataset
 from .binary_matrix import BinaryMatrixConfig, BinaryMatrixCurriculum, BinaryMatrixDataset
 from .caesar_cipher import CaesarCipherConfig, CaesarCipherDataset
@@ -46,6 +46,7 @@ __all__ = [
     "SpellBackwardDataset",
     "BaseConversionConfig",
     "BaseConversionDataset",
+    "BaseConversionCurriculum",
     "CaesarCipherConfig",
     "CaesarCipherDataset",
     "CryptarithmConfig",

reasoning_gym/algorithmic/base_conversion.py

@@ -4,6 +4,7 @@ from dataclasses import dataclass
 from random import Random
 from typing import Optional
 
+from ..coaching import AttributeType, BaseCurriculum, RangeAttributeDefinition
 from ..factory import ProceduralDataset, register_dataset
 
 QUESTION_TEMPLATE = """Your task is to convert a number between two different bases.
@@ -108,8 +109,41 @@ class BaseConversionDataset(ProceduralDataset):
                 "target_base": target_base,
                 "source_repr": source_repr,
                 "target_repr": target_repr,
+                "difficulty": {
+                    "value": value,
+                    "base": (source_base, target_base),
+                },
             },
         }
 
 
-register_dataset("base_conversion", BaseConversionDataset, BaseConversionConfig)
+class BaseConversionCurriculum(BaseCurriculum):
+    def __init__(self):
+        super().__init__(BaseConversionCurriculum.__name__, BaseConversionConfig)
+
+        # Define attributes
+        self._define_attributes(
+            RangeAttributeDefinition(
+                name="base",
+                levels=[9, 18, 27, 36],
+                default_level=0,
+                description="The base of the number system",
+                attr_type=AttributeType.APPEND,
+                min_value=2,
+                lower_field_name="min_base",
+                upper_field_name="max_base",
+            ),
+            RangeAttributeDefinition(
+                name="value",
+                levels=[1_000, 10_000, 100_000, 1_000_000],
+                default_level=0,
+                description="The value to convert",
+                attr_type=AttributeType.APPEND,
+                min_value=0,
+                lower_field_name="min_value",
+                upper_field_name="max_value",
+            ),
+        )
+
+
+register_dataset("base_conversion", BaseConversionDataset, BaseConversionConfig, BaseConversionCurriculum)

tests/test_base_conversion.py

@@ -2,7 +2,11 @@
 
 import pytest
 
-from reasoning_gym.algorithmic.base_conversion import BaseConversionConfig, BaseConversionDataset
+from reasoning_gym.algorithmic.base_conversion import (
+    BaseConversionConfig,
+    BaseConversionCurriculum,
+    BaseConversionDataset,
+)
 
 
 def test_base_conversion_config_validation():
@@ -163,3 +167,28 @@ def test_base_conversion_formatting():
         assert item["answer"].strip() == item["answer"]
         # Verify hint is included for bases > 10
         assert "use lowercase letters" in item["question"]
+
+
+def test_base_conversion__curriculum():
+    curriculum = BaseConversionCurriculum()
+
+    base_value = {"size": 150, "seed": 1}
+
+    base_cfg: BaseConversionConfig = curriculum.generate_configuration(base_value)
+    assert base_cfg.seed == 1
+    assert base_cfg.size == 150
+    assert base_cfg.min_base == 9 and base_cfg.max_base == 9
+    assert base_cfg.min_value == 1000 and base_cfg.max_value == 1000
+
+    # test incrementing attribute levels
+    curriculum.increment_attr_level("base")
+    curriculum.increment_attr_level("value")
+    increased_cfg = curriculum.generate_configuration(base_value)
+    assert increased_cfg.min_base == 9 and increased_cfg.max_base == 18
+    assert increased_cfg.min_value == 1000 and increased_cfg.max_value == 10000
+
+    # test decrementing attribute level for base again
+    curriculum.decrement_attr_level("base")
+    partially_decreased_cfg = curriculum.generate_configuration(base_value)
+    assert partially_decreased_cfg.min_base == 9 and partially_decreased_cfg.max_base == 9
+    assert partially_decreased_cfg.min_value == 1000 and partially_decreased_cfg.max_value == 10000