Module: tf_agents.bandits.agents.dropout_thompson_sampling_agent

A neural network based agent that implements Thompson sampling via dropout.

Implements an agent based on a neural network that predicts arm rewards. The neural network internally uses dropout to approximate Thompson sampling.

Classes

class DropoutThompsonSamplingAgent: A neural network based Thompson sampling agent.

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