banditpylib.learners.mab_collaborative_ftbai_learner
¶
Classes¶
MABCollaborativeFixedTimeBAILearner
: Collaborative fixed-time learner aiming to identify the best arm in theLilUCBHeuristicCollaborative
: Colaborative learner using lilucb heuristic as centralized policy
- class banditpylib.learners.mab_collaborative_ftbai_learner.MABCollaborativeFixedTimeBAILearner(agent: banditpylib.learners.mab_collaborative_ftbai_learner.utils.MABCollaborativeFixedTimeBAIAgent, master: banditpylib.learners.mab_collaborative_ftbai_learner.utils.MABCollaborativeFixedTimeBAIMaster, num_agents: int, name: Optional[str] = None)[source]¶
Collaborative fixed-time learner aiming to identify the best arm in the ordinary multi-armed bandit environment
- Parameters
agent (CollaborativeAgent) – one instance of an agent
master (CollaboratveMaster) – instance of the master
num_agents (int) – total number of agents involved
name (Optional[str]) – alias name
Inheritance
- property goal: banditpylib.learners.utils.Goal¶
Goal of the learner
- property running_environment: Union[type, List[type]]¶
Type of bandit environment the learner plays with
- class banditpylib.learners.mab_collaborative_ftbai_learner.LilUCBHeuristicCollaborative(num_agents: int, arm_num: int, rounds: int, horizon: int, name: Optional[str] = None)[source]¶
Colaborative learner using lilucb heuristic as centralized policy
- Parameters
num_agents (int) – number of agents
arm_num (int) – number of arms of the bandit
rounds (int) – number of total rounds allowed
horizon (int) – maximum number of pulls the agent can make (over all rounds combined)
name (Optional[str]) – alias name
Inheritance