reward_funcs.py 文件源码

def _pnl_pos(self, e, s, a, pnl, inputs):
        '''
        Return the reward based on PnL from the last step marked to the
        mid-price of the instruments traded

        :param e: Environment object. Environment where the agent operates
        :param a: Agent object. the agent that will perform the action
        :param s: dictionary. The inputs from environment to the agent
        :param pnl: float. The current pnl of the agent
        :param inputs: dictionary. The inputs from environment to the agent
        '''
        reward = self._pnl(e, s, a, pnl, inputs)
        s_main = e.s_main_intrument
        if not a.logged_action:
            return reward
        f_penalty = abs(e.agent_states[a][s_main]['Position']) * 0.02
        f_penalty += abs(np.around(a.log_info['duration'])) * 0.30
        return reward - f_penalty