tf_agents.policies.utils.PerArmPolicyInfo

PerArmPolicyInfo(log_probability, predicted_rewards_mean, multiobjective_scalarized_predicted_rewards_mean, predicted_rewards_optimistic, predicted_rewards_sampled, bandit_policy_type, chosen_arm_features)

tf_agents.policies.utils.PerArmPolicyInfo(
    log_probability=(),
    predicted_rewards_mean=(),
    multiobjective_scalarized_predicted_rewards_mean=(),
    predicted_rewards_optimistic=(),
    predicted_rewards_sampled=(),
    bandit_policy_type=(),
    chosen_arm_features=()
)

log_probability A namedtuple alias for field number 0 predicted_rewards_mean A namedtuple alias for field number 1 multiobjective_scalarized_predicted_rewards_mean A namedtuple alias for field number 2 predicted_rewards_optimistic A namedtuple alias for field number 3 predicted_rewards_sampled A namedtuple alias for field number 4 bandit_policy_type A namedtuple alias for field number 5 chosen_arm_features A namedtuple alias for field number 6