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=()
)

Attributes
`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

tf_agents.policies.utils.PerArmPolicyInfo

Attributes