banditpylib.learners.thresholding_bandit_learner

Classes

• ThresholdingBanditLearner: Abstract class for learners playing with thresholding bandit

• APT: Anytime Parameter-free Thresholding algorithm

• Uniform: Uniform Sampling

class banditpylib.learners.thresholding_bandit_learner.ThresholdingBanditLearner(arm_num: int, name: Optional[str])

Abstract class for learners playing with thresholding bandit

Parameters

• arm_num (int) – number of arms

• name (Optional[str]) – alias name

Inheritance

property arm_num: int

Number of arms

property running_environment: Union[type, List[type]]

Type of bandit environment the learner plays with

class banditpylib.learners.thresholding_bandit_learner.APT(arm_num: int, theta: float, eps: float, name: Optional[str] = None)

Anytime Parameter-free Thresholding algorithm [LGC16]

Parameters

• arm_num (int) – number of arms

• theta (float) – threshold

• eps (float) – radius of indifferent zone

• name (Optional[str]) – alias name

Inheritance

actions(context: data_pb2.Context) → data_pb2.Actions

Actions of the learner

Parameters

context – contextual information about the bandit environment

Returns

actions to take

property goal: banditpylib.learners.utils.Goal

Goal of the learner

reset()

Reset the learner

Warning

This function should be called before the start of the game.

update(feedback: data_pb2.Feedback)

Update the learner

Parameters

feedback – feedback returned by the bandit environment after actions() is executed

class banditpylib.learners.thresholding_bandit_learner.Uniform(arm_num: int, theta: float, eps: float, name: Optional[str] = None)

Uniform Sampling

Sample each arm in a round-robin way.

Parameters

• arm_num (int) – number of arms

• theta (float) – threshold

• eps (float) – radius of indifferent zone

• name (Optional[str]) – alias name

Inheritance

actions(context: data_pb2.Context) → data_pb2.Actions

Actions of the learner

Parameters

context – contextual information about the bandit environment

Returns

actions to take

property goal: banditpylib.learners.utils.Goal

Goal of the learner

reset()

Reset the learner

Warning

This function should be called before the start of the game.

update(feedback: data_pb2.Feedback)

Update the learner

Parameters

feedback – feedback returned by the bandit environment after actions() is executed