def __init__(self, name='AverageReturn', buffer_size=10, batch_size=None):
"""Creates an AverageReturnMetric."""
self._np_state = numpy_storage.NumpyState()
# Set a dummy value on self._np_state.episode_return so it gets included in
# the first checkpoint (before metric is first called).
self._np_state.episode_return = np.float64(0)
super(AverageReturnMetric, self).__init__(name, buffer_size=buffer_size,
batch_size=batch_size)
def testSaveRestore(self):
arrays = numpy_storage.NumpyState()
checkpoint = tf.train.Checkpoint(numpy_arrays=arrays)
arrays.x = np.ones([3, 4])
directory = self.get_temp_dir()
prefix = os.path.join(directory, 'ckpt')
save_path = checkpoint.save(prefix)
arrays.x[:] = 0.
self.assertAllEqual(arrays.x, np.zeros([3, 4]))
checkpoint.restore(save_path).assert_consumed()
self.assertAllEqual(arrays.x, np.ones([3, 4]))
second_checkpoint = tf.train.Checkpoint(
numpy_arrays=numpy_storage.NumpyState())
# Attributes of NumpyState objects are created automatically by restore()
second_checkpoint.restore(save_path).assert_consumed()
self.assertAllEqual(np.ones([3, 4]), second_checkpoint.numpy_arrays.x)
def __init__(self, data_spec, capacity):
"""Creates a PyUniformReplayBuffer.
Args:
data_spec: An ArraySpec or a list/tuple/nest of ArraySpecs describing a
single item that can be stored in this buffer.
capacity: The maximum number of items that can be stored in the buffer.
"""
super(PyUniformReplayBuffer, self).__init__(data_spec, capacity)
self._storage = numpy_storage.NumpyStorage(self._encoded_data_spec(),
capacity)
self._lock = threading.Lock()
self._np_state = numpy_storage.NumpyState()
# Adding elements to the replay buffer is done in a circular way.
# Keeps track of the actual size of the replay buffer and the location
# where to add new elements.
self._np_state.size = np.int64(0)
self._np_state.cur_id = np.int64(0)
# Total number of items that went through the replay buffer.
self._np_state.item_count = np.int64(0)
def __init__(self, name='Counter'): super(CounterMetric, self).__init__(name) self._np_state = numpy_storage.NumpyState() self.reset()
def __init__(self, name='NumberOfEpisodes'): super(NumberOfEpisodes, self).__init__(name) self._np_state = numpy_storage.NumpyState() self.reset()
def __init__(self, name='EnvironmentSteps'): super(EnvironmentSteps, self).__init__(name) self._np_state = numpy_storage.NumpyState() self.reset()