oa::ml::training::PpoUpdateProgram
Reusable fixed-geometry PPO backward and AdamW programs. Retain this value across trainers when checkpointing between rollouts. Each minibatch reuses one bounded tape’s storage, accumulating sample-weighted gradients before exactly one AdamW step per epoch. Tail shapes compile once. Drop never submits or waits. Different models/configurations are rejected.
Declaration
pub struct PpoUpdateProgram { /* private fields */ }Public Rust declaration.
Public Methods
Associated Functions
Public 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.
No public source comment is attached to this declaration.