trinity.algorithm.policy_loss_fn.topr_policy_loss module#
TOPR policy loss function. Refer to https://arxiv.org/pdf/2503.14286v1
- class trinity.algorithm.policy_loss_fn.topr_policy_loss.TOPRPolicyLossFn(backend: str = 'verl', advantage_threshold: float = 0.0, loss_agg_mode: str = 'token-mean')[源代码]#
基类：
PolicyLossFn- __init__(backend: str = 'verl', advantage_threshold: float = 0.0, loss_agg_mode: str = 'token-mean') None[源代码]#
Initialize the policy loss function.
- 参数:
backend -- The training framework/backend to use (e.g., "verl")
- classmethod default_args() Dict[源代码]#
Get default initialization arguments for this loss function.
- 返回:
The default init arguments for the policy loss function.
- 返回类型:
Dict
- property select_keys#
Returns parameter keys mapped to the specific training framework's naming convention.