tf_agents.agents.ppo.ppo_agent.PPOLossInfo

PPOLossInfo(policy_gradient_loss, value_estimation_loss, l2_regularization_loss, entropy_regularization_loss, kl_penalty_loss, clip_fraction)

tf_agents.agents.ppo.ppo_agent.PPOLossInfo(
    policy_gradient_loss,
    value_estimation_loss,
    l2_regularization_loss,
    entropy_regularization_loss,
    kl_penalty_loss,
    clip_fraction
)

Attributes
`policy_gradient_loss`	A `namedtuple` alias for field number 0
`value_estimation_loss`	A `namedtuple` alias for field number 1
`l2_regularization_loss`	A `namedtuple` alias for field number 2
`entropy_regularization_loss`	A `namedtuple` alias for field number 3
`kl_penalty_loss`	A `namedtuple` alias for field number 4
`clip_fraction`	A `namedtuple` alias for field number 5

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2024-04-26 UTC.

English
中文 – 简体

tf_agents.agents.ppo.ppo_agent.PPOLossInfo

Attributes