|View source on GitHub|
A collection of variables used by subclasses of
tf_agents.bandits.agents.exp3_mixture_agent.Exp3MixtureVariableCollection( num_agents: int, reward_aggregates: Optional[List[float]] = None, inverse_temperature: float = 0.0 )
Note that this variable collection only contains the mixture weights. The variables of the sub-agents that the mixture agent mixes are in variable collections of the respective sub-agents.