tf_agents.agents.ppo.ppo_agent.PPOLossInfo

Stay organized with collections Save and categorize content based on your preferences.

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

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