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

tf_agents.bandits.policies.policy_utilities.PolicyInfo

View source on GitHub

PolicyInfo(log_probability, predicted_rewards_mean, predicted_rewards_sampled, bandit_policy_type)

@staticmethod
tf_agents.bandits.policies.policy_utilities.PolicyInfo(
    _cls, log_probability=(), predicted_rewards_mean=(),
    predicted_rewards_sampled=(), bandit_policy_type=()
)

Attributes:

  • log_probability
  • predicted_rewards_mean
  • predicted_rewards_sampled
  • bandit_policy_type