ML Community Day is November 9! Join us for updates from TensorFlow, JAX, and more Learn more

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.


class DropoutThompsonSamplingAgent: A neural network based Thompson sampling agent.