trinity.algorithm.advantage_fn.rloo_advantage module
RLOO advantage computation
Ref: volcengine/verl
-
class trinity.algorithm.advantage_fn.rloo_advantage.RLOOAdvantageFn[source]
Bases: AdvantageFn
-
__init__() → None[source]
-
classmethod default_args() → Dict[source]
- Returns:
The default init arguments for the advantage function.
- Return type:
Dict