modified_humanoid.py 文件源码

def _step(self, a):
        pos_before = mass_center(self.model)
        self.do_simulation(a, self.frame_skip)
        pos_after = mass_center(self.model)

        pos_after_standup =  self.model.data.qpos[2][0]

        down = bool(( self.model.data.qpos[2] < 1.0) or ( self.model.data.qpos[2] > 2.0))

        alive_bonus = 5.0 if not down else 1.0

        data = self.model.data

        uph_cost = (pos_after_standup - 0) / self.model.opt.timestep
        lin_vel_cost = 0.25 * (pos_after - pos_before) / self.model.opt.timestep

        quad_ctrl_cost = 0.1 * np.square(data.ctrl).sum()
        quad_impact_cost = .5e-6 * np.square(data.cfrc_ext).sum()
        quad_impact_cost = min(quad_impact_cost, 10)

        reward = lin_vel_cost + uph_cost - quad_ctrl_cost - quad_impact_cost + alive_bonus
        qpos = self.model.data.qpos

        done = bool(False)
        return self._get_obs(), reward, done, dict(reward_linup=uph_cost, reward_quadctrl=-quad_ctrl_cost, reward_impact=-quad_impact_cost, reward_alive=alive_bonus)