oa::ml::training::PpoTrainerMetrics
Scalar results from the last completed PPO update epoch.
Declaration
pub struct PpoTrainerMetrics { pub rollout: u64, pub update_epoch: u64, pub total_loss: f32, pub policy_loss: f32, pub value_loss: f32, pub entropy: f32, }Public Rust declaration.
Public Methods
Associated Functions
Public Data Members
rolloutu64fieldupdate_epochu64fieldtotal_lossf32fieldpolicy_lossf32fieldvalue_lossf32fieldentropyf32fieldPublic Method Documentation
No public source comment is attached to this declaration.
No public source comment is attached to this declaration.
No public source comment is attached to this declaration.
No public source comment is attached to this declaration.