environment.py 文件源码

def step(self, action, mode):
        qvel, qpos = [], []
        if mode == 'tensorflow':
            if self.random_initialization:
                state, reward, done, qval, qpos = tf.py_func(self._step, inp=[action], Tout=[tf.float32, tf.float32, tf.bool, tf.float32, tf.float32], name='env_step_func')
            else:
                state, reward, done = tf.py_func(self._step, inp=[action],
                                                 Tout=[tf.float32, tf.float32, tf.bool],
                                                 name='env_step_func')

            state = tf.reshape(state, shape=(self.state_size,))
            done.set_shape(())
        else:
            if self.random_initialization:
                state, reward, done, qvel, qpos = self._step(action)
            else:
                state, reward, done = self._step(action)

        return state, reward, done, 0., qvel, qpos