reagent.ope package

Subpackages

• reagent.ope.datasets package
  • Submodules
  • reagent.ope.datasets.logged_dataset module
  • Module contents
• reagent.ope.estimators package
  • Submodules
  • reagent.ope.estimators.contextual_bandits_estimators module
  • reagent.ope.estimators.estimator module
  • reagent.ope.estimators.sequential_estimators module
  • reagent.ope.estimators.slate_estimators module
  • reagent.ope.estimators.types module
  • Module contents
• reagent.ope.test package
  • Subpackages
    • reagent.ope.test.unit_tests package
      • Submodules
      • reagent.ope.test.unit_tests.test_slate_estimators module
      • reagent.ope.test.unit_tests.test_types module
      • reagent.ope.test.unit_tests.test_utils module
      • Module contents
  • Submodules
  • reagent.ope.test.envs module
  • reagent.ope.test.gridworld module
  • reagent.ope.test.mslr_slate module
  • reagent.ope.test.multiclass_bandits module
  • reagent.ope.test.yandex_web_search module
  • Module contents
• reagent.ope.trainers package
  • Submodules
  • reagent.ope.trainers.linear_trainers module
  • reagent.ope.trainers.rl_tabular_trainers module
  • Module contents

Submodules

reagent.ope.utils module

class reagent.ope.utils.Clamper(min_v: float = -inf, max_v: float = inf)

Bases: object

class reagent.ope.utils.LRUCache(maxsize=1024, *args, **kwds)

Bases: collections.OrderedDict

class reagent.ope.utils.RunningAverage(init_val: float = nan)

Bases: object

add(value) → reagent.ope.utils.RunningAverage

property average

property count

property total

reagent.ope.utils.convert_to_one_hots(a, num_classes: int, dtype=torch.int, device=None)

Convert class index array (num_sample,) to an one hots array (num_sample, num_classes)

Parameters

• a – index array

• num_classes – number of classes

• dtype – data type

Returns

one hots array in shape of (a.shape[0], num_classes)

Module contents