oa::ReplayBuffer
Preallocated circular off-policy storage. Appends and deterministic uniform sampling stay on the GPU; size/cursor are host control metadata and never depend on a tensor readback.
Public Methods
Static Public Methods
Public Method Documentation
No public source comment is attached to this declaration.
Parameters
inTransitionconst ReplayTransition &—
Returns
oa::StatusThe declared return value.
No public source comment is attached to this declaration.
Returns
oa::U32The declared return value.
No public source comment is attached to this declaration.
Returns
const ReplayConfig &The declared return value.
No public source comment is attached to this declaration.
Returns
oa::U32The declared return value.
No public source comment is attached to this declaration.
Returns
boolThe declared return value.
No public source comment is attached to this declaration.
Returns
boolThe declared return value.
No public source comment is attached to this declaration.
Returns
voidThe declared return value.
No public source comment is attached to this declaration.
Parameters
inBatchSizeoa::U32—
inSeedoa::U64—
Returns
oa::Result<ReplayBatch>The declared return value.
No public source comment is attached to this declaration.
Returns
oa::U32The declared return value.
No public source comment is attached to this declaration.
Parameters
inConfigconst ReplayConfig &—
Returns
oa::Result<ReplayBuffer>The declared return value.