Google I/O is a wrap! Catch up on TensorFlow sessions View sessions

Module: tf_agents.bandits.agents.exp3_mixture_agent

A mixture agent that updates the mixture distribution based on EXP3.

For a reference on EXP3, see Bandit Algorithms by Tor Lattimore and Csaba Szepesvari (https://tor-lattimore.com/downloads/book/book.pdf).

Classes

class Exp3MixtureAgent: An agent that mixes a set of agents and updates the weights with Exp3.

class Exp3MixtureVariableCollection: A collection of variables used by subclasses of MixtureAgent.

absolute_import Instance of __future__._Feature
division Instance of __future__._Feature
print_function Instance of __future__._Feature