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

tf_agents.agents.ppo.ppo_agent.PPOLossInfo

View source on GitHub

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

@staticmethod
tf_agents.agents.ppo.ppo_agent.PPOLossInfo(
    _cls, policy_gradient_loss, value_estimation_loss, l2_regularization_loss,
    entropy_regularization_loss, kl_penalty_loss
)

Attributes:

  • policy_gradient_loss
  • value_estimation_loss
  • l2_regularization_loss
  • entropy_regularization_loss
  • kl_penalty_loss