Method update

numpy_ml/rl_models/agents.py:87–98

r""" Update the agent parameters according to the rewards accrued on the current episode. Returns ------- avg_reward : float The average reward earned by the best `retain_prcnt` theta samples on the current episode.

(self)

    @abstractmethod
    def update(self):
        r"""
        Update the agent parameters according to the rewards accrued on the
        current episode.

        Returns
        -------
        avg_reward : float
            The average reward earned by the best `retain_prcnt` theta samples
            on the current episode.
        """
        raise NotImplementedError


class CrossEntropyAgent(AgentBase):