def __init__(self, data_spec, capacity, alpha=0.6):
"""
Params:
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.
alpha: α determines how much prioritization is used, with α = 0 corresponding to the uniform case.
"""
super(PyPrioritizedReplayBuffer, self).__init__(data_spec, capacity)
logger.info("Creating an instance of %s. Params: data_spec: %s, capacity: %s, alpha: %s" %
(str(type(self).__name__), str(data_spec), str(capacity), str(alpha)))
# State variables needed to maintain the replay buffer. These were copied from the uniform replay buffer
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)
self._prioritized_buffer_alpha = alpha
self._prioritized_buffer_capacity = capacity
# an array in which we keep track of the priorities. The size of this array is equal to the size of the replay
# buffer. Items stored at a given index in the Priority array map to the experience at the same index in the
# buffer. The content of the items in the priority array represent the loss of their respective experience the
# last time that experience was used for training.
self._prioritized_buffer_priorities = np.zeros((capacity,), dtype=np.float32)
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)