Method update

verl/trainer/ppo/core_algos.py:183–190

Update method for fixed KL controller (no-op). Args: current_kl (float): Current KL divergence value (unused). n_steps (int): Number of steps taken (unused).

(self, current_kl, n_steps)

        self.value = kl_coef

    def update(self, current_kl, n_steps):
        """Update method for fixed KL controller (no-op).

        Args:
            current_kl (float): Current KL divergence value (unused).
            n_steps (int): Number of steps taken (unused).
        """
        pass


def get_kl_controller(kl_ctrl):