tf_agents.policies.utils.bandit_policy_uniform_mask

Set bandit policy type tensor to BanditPolicyType.UNIFORM based on mask.

tf_agents.policies.utils.bandit_policy_uniform_mask(
    values: tf_agents.typing.types.Tensor,
    mask: tf_agents.typing.types.Tensor
) -> tf_agents.typing.types.Tensor

Set bandit policy type values to BanditPolicyType.UNIFORM; returns tensor where output[i] is BanditPolicyType.UNIFORM if mask[i] is True, otherwise it is left as values[i].

values Tensor containing BanditPolicyType enumerations.
mask Tensor of the same shape as values with boolean flags indicating values to set to BanditPolicyType.UNIFORM.

Tensor containing BanditPolicyType enumerations with masked values.