Missed TensorFlow Dev Summit? Check out the video playlist. Watch recordings

Module: tf_agents.bandits.networks.heteroscedastic_q_network

View source on GitHub

Network Outputting Expected Value and Variance of Rewards.

Classes

class HeteroscedasticQNetwork: Network Outputting Expected Value and Variance of Rewards.

class QBanditNetworkResult: QBanditNetworkResult(q_value_logits, log_variance)