def reset(self, indices=None, max_frames=None, name=None): '''Resets Atari instances with a random noop start (1-30) and set the maximum number of frames for the episode (default 100,000 * frameskip) ''' with tf.variable_scope(name, default_name='MazeReset'): noops = tf.random_uniform(tf.shape(indices), minval=1, maxval=31, dtype=tf.int32) if max_frames is None: max_frames = self.env_default_timestep_cutoff return gym_tensorflow_module.environment_reset(self.instances, indices, noops=noops, max_frames=max_frames)
def reset(self, indices=None, max_frames=None, name=None): '''Resets Atari instances with a random noop start (1-30) and set the maximum number of frames for the episode (default 100,000 * frameskip) ''' if indices is None: indices = np.arange(self.batch_size) with tf.variable_scope(name, default_name='AtariReset'): noops = tf.random_uniform(tf.shape(indices), minval=1, maxval=31, dtype=tf.int32) if max_frames is None: max_frames = tf.ones_like(indices, dtype=tf.int32) * (100000 * self.frameskip) import collections if not isinstance(max_frames, collections.Sequence): max_frames = tf.ones_like(indices, dtype=tf.int32) * max_frames return gym_tensorflow_module.environment_reset(self.instances, indices, noops=noops, max_frames=max_frames)