trinity.algorithm.advantage_fn.remax_advantage module

trinity.algorithm.advantage_fn.remax_advantage module#

REMAX advantage computation

Ref: volcengine/verl

class trinity.algorithm.advantage_fn.remax_advantage.REMAXAdvantageFn[source]#

Bases: AdvantageFn

__init__() None[source]#
classmethod default_args() Dict[source]#
Returns:

The default init arguments for the advantage function.

Return type:

Dict