Python源码示例：baselines.common.segment.MinSegmentTree()
示例1
def __init__(self,
limit,
alpha,
transition_small_epsilon=1e-6,
demo_epsilon=0.2,
nb_rollout_steps=100):
super(PrioritizedMemory, self).__init__(limit, nb_rollout_steps)
assert alpha > 0
self._alpha = alpha
self._transition_small_epsilon = transition_small_epsilon
self._demo_epsilon = demo_epsilon
it_capacity = 1
while it_capacity < self.maxsize:
it_capacity *= 2 # Size must be power of 2
self._it_sum = SumSegmentTree(it_capacity)
self._it_min = MinSegmentTree(it_capacity)
self._max_priority = 1.0
示例2
def __init__(self, size, alpha, epsilon, timesteps, initial_p, final_p):
super(DoublePrioritizedReplayBuffer, self).__init__(size)
assert alpha > 0
self._alpha = alpha
self._epsilon = epsilon
self._beta_schedule = LinearSchedule(timesteps, initial_p=initial_p, final_p=final_p)
it_capacity = 1
while it_capacity < size:
it_capacity *= 2
self._it_sum = SumSegmentTree(it_capacity)
self._it_min = MinSegmentTree(it_capacity)
self._max_priority = 1.0
self._it_sum2 = SumSegmentTree(it_capacity)
self._it_min2 = MinSegmentTree(it_capacity)
self._max_priority2 = 1.0
示例3
def __init__(self, size, alpha):
"""Create Prioritized Replay buffer.
Parameters
----------
size: int
Max number of transitions to store in the buffer. When the buffer
overflows the old memories are dropped.
alpha: float
how much prioritization is used
(0 - no prioritization, 1 - full prioritization)
See Also
--------
ReplayBuffer.__init__
"""
super(PrioritizedReplayBuffer, self).__init__(size)
assert alpha > 0
self._alpha = alpha
it_capacity = 1
while it_capacity < size:
it_capacity *= 2
self._it_sum = SumSegmentTree(it_capacity)
self._it_min = MinSegmentTree(it_capacity)
self._max_priority = 1.0
示例4
def __init__(self, size, alpha):
"""Create Prioritized Replay buffer.
Parameters
----------
size: int
Max number of transitions to store in the buffer. When the buffer
overflows the old memories are dropped.
alpha: float
how much prioritization is used
(0 - no prioritization, 1 - full prioritization)
See Also
--------
ReplayBuffer.__init__
"""
super(PrioritizedReplayBuffer, self).__init__(size)
assert alpha > 0
self._alpha = alpha
it_capacity = 1
while it_capacity < size:
it_capacity *= 2
self._it_sum = SumSegmentTree(it_capacity)
self._it_min = MinSegmentTree(it_capacity)
self._max_priority = 1.0
示例5
def test_max_interval_tree():
tree = MinSegmentTree(4)
tree[0] = 1.0
tree[2] = 0.5
tree[3] = 3.0
assert np.isclose(tree.min(), 0.5)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 0.5)
assert np.isclose(tree.min(0, -1), 0.5)
assert np.isclose(tree.min(2, 4), 0.5)
assert np.isclose(tree.min(3, 4), 3.0)
tree[2] = 0.7
assert np.isclose(tree.min(), 0.7)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 0.7)
assert np.isclose(tree.min(0, -1), 0.7)
assert np.isclose(tree.min(2, 4), 0.7)
assert np.isclose(tree.min(3, 4), 3.0)
tree[2] = 4.0
assert np.isclose(tree.min(), 1.0)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 1.0)
assert np.isclose(tree.min(0, -1), 1.0)
assert np.isclose(tree.min(2, 4), 3.0)
assert np.isclose(tree.min(2, 3), 4.0)
assert np.isclose(tree.min(2, -1), 4.0)
assert np.isclose(tree.min(3, 4), 3.0)
示例6
def __init__(self, size, alpha):
"""Create Prioritized Replay buffer.
Parameters
----------
size: int
Max number of transitions to store in the buffer. When the buffer
overflows the old memories are dropped.
alpha: float
how much prioritization is used
(0 - no prioritization, 1 - full prioritization)
See Also
--------
ReplayBuffer.__init__
"""
super(PrioritizedReplayBuffer, self).__init__(size)
assert alpha >= 0
self._alpha = alpha
it_capacity = 1
while it_capacity < size:
it_capacity *= 2
self._it_sum = SumSegmentTree(it_capacity)
self._it_min = MinSegmentTree(it_capacity)
self._max_priority = 1.0
示例7
def test_max_interval_tree():
tree = MinSegmentTree(4)
tree[0] = 1.0
tree[2] = 0.5
tree[3] = 3.0
assert np.isclose(tree.min(), 0.5)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 0.5)
assert np.isclose(tree.min(0, -1), 0.5)
assert np.isclose(tree.min(2, 4), 0.5)
assert np.isclose(tree.min(3, 4), 3.0)
tree[2] = 0.7
assert np.isclose(tree.min(), 0.7)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 0.7)
assert np.isclose(tree.min(0, -1), 0.7)
assert np.isclose(tree.min(2, 4), 0.7)
assert np.isclose(tree.min(3, 4), 3.0)
tree[2] = 4.0
assert np.isclose(tree.min(), 1.0)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 1.0)
assert np.isclose(tree.min(0, -1), 1.0)
assert np.isclose(tree.min(2, 4), 3.0)
assert np.isclose(tree.min(2, 3), 4.0)
assert np.isclose(tree.min(2, -1), 4.0)
assert np.isclose(tree.min(3, 4), 3.0)
示例8
def test_max_interval_tree():
tree = MinSegmentTree(4)
tree[0] = 1.0
tree[2] = 0.5
tree[3] = 3.0
assert np.isclose(tree.min(), 0.5)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 0.5)
assert np.isclose(tree.min(0, -1), 0.5)
assert np.isclose(tree.min(2, 4), 0.5)
assert np.isclose(tree.min(3, 4), 3.0)
tree[2] = 0.7
assert np.isclose(tree.min(), 0.7)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 0.7)
assert np.isclose(tree.min(0, -1), 0.7)
assert np.isclose(tree.min(2, 4), 0.7)
assert np.isclose(tree.min(3, 4), 3.0)
tree[2] = 4.0
assert np.isclose(tree.min(), 1.0)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 1.0)
assert np.isclose(tree.min(0, -1), 1.0)
assert np.isclose(tree.min(2, 4), 3.0)
assert np.isclose(tree.min(2, 3), 4.0)
assert np.isclose(tree.min(2, -1), 4.0)
assert np.isclose(tree.min(3, 4), 3.0)
示例9
def test_max_interval_tree():
tree = MinSegmentTree(4)
tree[0] = 1.0
tree[2] = 0.5
tree[3] = 3.0
assert np.isclose(tree.min(), 0.5)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 0.5)
assert np.isclose(tree.min(0, -1), 0.5)
assert np.isclose(tree.min(2, 4), 0.5)
assert np.isclose(tree.min(3, 4), 3.0)
tree[2] = 0.7
assert np.isclose(tree.min(), 0.7)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 0.7)
assert np.isclose(tree.min(0, -1), 0.7)
assert np.isclose(tree.min(2, 4), 0.7)
assert np.isclose(tree.min(3, 4), 3.0)
tree[2] = 4.0
assert np.isclose(tree.min(), 1.0)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 1.0)
assert np.isclose(tree.min(0, -1), 1.0)
assert np.isclose(tree.min(2, 4), 3.0)
assert np.isclose(tree.min(2, 3), 4.0)
assert np.isclose(tree.min(2, -1), 4.0)
assert np.isclose(tree.min(3, 4), 3.0)
示例10
def test_max_interval_tree():
tree = MinSegmentTree(4)
tree[0] = 1.0
tree[2] = 0.5
tree[3] = 3.0
assert np.isclose(tree.min(), 0.5)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 0.5)
assert np.isclose(tree.min(0, -1), 0.5)
assert np.isclose(tree.min(2, 4), 0.5)
assert np.isclose(tree.min(3, 4), 3.0)
tree[2] = 0.7
assert np.isclose(tree.min(), 0.7)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 0.7)
assert np.isclose(tree.min(0, -1), 0.7)
assert np.isclose(tree.min(2, 4), 0.7)
assert np.isclose(tree.min(3, 4), 3.0)
tree[2] = 4.0
assert np.isclose(tree.min(), 1.0)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 1.0)
assert np.isclose(tree.min(0, -1), 1.0)
assert np.isclose(tree.min(2, 4), 3.0)
assert np.isclose(tree.min(2, 3), 4.0)
assert np.isclose(tree.min(2, -1), 4.0)
assert np.isclose(tree.min(3, 4), 3.0)
示例11
def __init__(self, size, alpha):
"""Create Prioritized Replay buffer.
Parameters
----------
size: int
Max number of transitions to store in the buffer. When the buffer
overflows the old memories are dropped.
alpha: float
how much prioritization is used
(0 - no prioritization, 1 - full prioritization)
See Also
--------
ReplayBuffer.__init__
"""
super(PrioritizedReplayBuffer, self).__init__(size)
assert alpha > 0
self._alpha = alpha
it_capacity = 1
while it_capacity < size:
it_capacity *= 2
self._it_sum = SumSegmentTree(it_capacity)
self._it_min = MinSegmentTree(it_capacity)
self._max_priority = 1.0
示例12
def test_max_interval_tree():
tree = MinSegmentTree(4)
tree[0] = 1.0
tree[2] = 0.5
tree[3] = 3.0
assert np.isclose(tree.min(), 0.5)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 0.5)
assert np.isclose(tree.min(0, -1), 0.5)
assert np.isclose(tree.min(2, 4), 0.5)
assert np.isclose(tree.min(3, 4), 3.0)
tree[2] = 0.7
assert np.isclose(tree.min(), 0.7)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 0.7)
assert np.isclose(tree.min(0, -1), 0.7)
assert np.isclose(tree.min(2, 4), 0.7)
assert np.isclose(tree.min(3, 4), 3.0)
tree[2] = 4.0
assert np.isclose(tree.min(), 1.0)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 1.0)
assert np.isclose(tree.min(0, -1), 1.0)
assert np.isclose(tree.min(2, 4), 3.0)
assert np.isclose(tree.min(2, 3), 4.0)
assert np.isclose(tree.min(2, -1), 4.0)
assert np.isclose(tree.min(3, 4), 3.0)
示例13
def __init__(self, size, alpha):
"""Create Prioritized Replay buffer.
Parameters
----------
size: int
Max number of transitions to store in the buffer. When the buffer
overflows the old memories are dropped.
alpha: float
how much prioritization is used
(0 - no prioritization, 1 - full prioritization)
See Also
--------
ReplayBuffer.__init__
"""
super(PrioritizedReplayBuffer, self).__init__(size)
assert alpha > 0
self._alpha = alpha
it_capacity = 1
while it_capacity < size:
it_capacity *= 2
self._it_sum = SumSegmentTree(it_capacity)
self._it_min = MinSegmentTree(it_capacity)
self._max_priority = 1.0
示例14
def test_max_interval_tree():
tree = MinSegmentTree(4)
tree[0] = 1.0
tree[2] = 0.5
tree[3] = 3.0
assert np.isclose(tree.min(), 0.5)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 0.5)
assert np.isclose(tree.min(0, -1), 0.5)
assert np.isclose(tree.min(2, 4), 0.5)
assert np.isclose(tree.min(3, 4), 3.0)
tree[2] = 0.7
assert np.isclose(tree.min(), 0.7)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 0.7)
assert np.isclose(tree.min(0, -1), 0.7)
assert np.isclose(tree.min(2, 4), 0.7)
assert np.isclose(tree.min(3, 4), 3.0)
tree[2] = 4.0
assert np.isclose(tree.min(), 1.0)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 1.0)
assert np.isclose(tree.min(0, -1), 1.0)
assert np.isclose(tree.min(2, 4), 3.0)
assert np.isclose(tree.min(2, 3), 4.0)
assert np.isclose(tree.min(2, -1), 4.0)
assert np.isclose(tree.min(3, 4), 3.0)
示例15
def __init__(self, size, alpha):
"""Create Prioritized Replay buffer.
Parameters
----------
size: int
Max number of transitions to store in the buffer. When the buffer
overflows the old memories are dropped.
alpha: float
how much prioritization is used
(0 - no prioritization, 1 - full prioritization)
See Also
--------
ReplayBuffer.__init__
"""
super(PrioritizedReplayBuffer, self).__init__(size)
assert alpha > 0
self._alpha = alpha
it_capacity = 1
while it_capacity < size:
it_capacity *= 2
self._it_sum = SumSegmentTree(it_capacity)
self._it_min = MinSegmentTree(it_capacity)
self._max_priority = 1.0
示例16
def test_max_interval_tree():
tree = MinSegmentTree(4)
tree[0] = 1.0
tree[2] = 0.5
tree[3] = 3.0
assert np.isclose(tree.min(), 0.5)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 0.5)
assert np.isclose(tree.min(0, -1), 0.5)
assert np.isclose(tree.min(2, 4), 0.5)
assert np.isclose(tree.min(3, 4), 3.0)
tree[2] = 0.7
assert np.isclose(tree.min(), 0.7)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 0.7)
assert np.isclose(tree.min(0, -1), 0.7)
assert np.isclose(tree.min(2, 4), 0.7)
assert np.isclose(tree.min(3, 4), 3.0)
tree[2] = 4.0
assert np.isclose(tree.min(), 1.0)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 1.0)
assert np.isclose(tree.min(0, -1), 1.0)
assert np.isclose(tree.min(2, 4), 3.0)
assert np.isclose(tree.min(2, 3), 4.0)
assert np.isclose(tree.min(2, -1), 4.0)
assert np.isclose(tree.min(3, 4), 3.0)
示例17
def __init__(self, size, alpha):
"""Create Prioritized Replay buffer.
Parameters
----------
size: int
Max number of transitions to store in the buffer. When the buffer
overflows the old memories are dropped.
alpha: float
how much prioritization is used
(0 - no prioritization, 1 - full prioritization)
See Also
--------
ReplayBuffer.__init__
"""
super(PrioritizedReplayBuffer, self).__init__(size)
assert alpha >= 0
self._alpha = alpha
it_capacity = 1
while it_capacity < size:
it_capacity *= 2
self._it_sum = SumSegmentTree(it_capacity)
self._it_min = MinSegmentTree(it_capacity)
self._max_priority = 1.0
示例18
def test_max_interval_tree():
tree = MinSegmentTree(4)
tree[0] = 1.0
tree[2] = 0.5
tree[3] = 3.0
assert np.isclose(tree.min(), 0.5)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 0.5)
assert np.isclose(tree.min(0, -1), 0.5)
assert np.isclose(tree.min(2, 4), 0.5)
assert np.isclose(tree.min(3, 4), 3.0)
tree[2] = 0.7
assert np.isclose(tree.min(), 0.7)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 0.7)
assert np.isclose(tree.min(0, -1), 0.7)
assert np.isclose(tree.min(2, 4), 0.7)
assert np.isclose(tree.min(3, 4), 3.0)
tree[2] = 4.0
assert np.isclose(tree.min(), 1.0)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 1.0)
assert np.isclose(tree.min(0, -1), 1.0)
assert np.isclose(tree.min(2, 4), 3.0)
assert np.isclose(tree.min(2, 3), 4.0)
assert np.isclose(tree.min(2, -1), 4.0)
assert np.isclose(tree.min(3, 4), 3.0)
示例19
def __init__(self, size, alpha):
"""Create Prioritized Replay buffer.
Parameters
----------
size: int
Max number of transitions to store in the buffer. When the buffer
overflows the old memories are dropped.
alpha: float
how much prioritization is used
(0 - no prioritization, 1 - full prioritization)
See Also
--------
ReplayBuffer.__init__
"""
super(PrioritizedReplayBuffer, self).__init__(size)
assert alpha >= 0
self._alpha = alpha
it_capacity = 1
while it_capacity < size:
it_capacity *= 2
self._it_sum = SumSegmentTree(it_capacity)
self._it_min = MinSegmentTree(it_capacity)
self._max_priority = 1.0
示例20
def test_max_interval_tree():
tree = MinSegmentTree(4)
tree[0] = 1.0
tree[2] = 0.5
tree[3] = 3.0
assert np.isclose(tree.min(), 0.5)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 0.5)
assert np.isclose(tree.min(0, -1), 0.5)
assert np.isclose(tree.min(2, 4), 0.5)
assert np.isclose(tree.min(3, 4), 3.0)
tree[2] = 0.7
assert np.isclose(tree.min(), 0.7)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 0.7)
assert np.isclose(tree.min(0, -1), 0.7)
assert np.isclose(tree.min(2, 4), 0.7)
assert np.isclose(tree.min(3, 4), 3.0)
tree[2] = 4.0
assert np.isclose(tree.min(), 1.0)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 1.0)
assert np.isclose(tree.min(0, -1), 1.0)
assert np.isclose(tree.min(2, 4), 3.0)
assert np.isclose(tree.min(2, 3), 4.0)
assert np.isclose(tree.min(2, -1), 4.0)
assert np.isclose(tree.min(3, 4), 3.0)
示例21
def test_max_interval_tree():
tree = MinSegmentTree(4)
tree[0] = 1.0
tree[2] = 0.5
tree[3] = 3.0
assert np.isclose(tree.min(), 0.5)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 0.5)
assert np.isclose(tree.min(0, -1), 0.5)
assert np.isclose(tree.min(2, 4), 0.5)
assert np.isclose(tree.min(3, 4), 3.0)
tree[2] = 0.7
assert np.isclose(tree.min(), 0.7)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 0.7)
assert np.isclose(tree.min(0, -1), 0.7)
assert np.isclose(tree.min(2, 4), 0.7)
assert np.isclose(tree.min(3, 4), 3.0)
tree[2] = 4.0
assert np.isclose(tree.min(), 1.0)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 1.0)
assert np.isclose(tree.min(0, -1), 1.0)
assert np.isclose(tree.min(2, 4), 3.0)
assert np.isclose(tree.min(2, 3), 4.0)
assert np.isclose(tree.min(2, -1), 4.0)
assert np.isclose(tree.min(3, 4), 3.0)
示例22
def __init__(self, size, alpha):
"""Create Prioritized Replay buffer.
Parameters
----------
size: int
Max number of transitions to store in the buffer. When the buffer
overflows the old memories are dropped.
alpha: float
how much prioritization is used
(0 - no prioritization, 1 - full prioritization)
See Also
--------
ReplayBuffer.__init__
"""
super(PrioritizedReplayBuffer, self).__init__(size)
assert alpha > 0
self._alpha = alpha
it_capacity = 1
while it_capacity < size:
it_capacity *= 2
self._it_sum = SumSegmentTree(it_capacity)
self._it_min = MinSegmentTree(it_capacity)
self._max_priority = 1.0
示例23
def test_max_interval_tree():
tree = MinSegmentTree(4)
tree[0] = 1.0
tree[2] = 0.5
tree[3] = 3.0
assert np.isclose(tree.min(), 0.5)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 0.5)
assert np.isclose(tree.min(0, -1), 0.5)
assert np.isclose(tree.min(2, 4), 0.5)
assert np.isclose(tree.min(3, 4), 3.0)
tree[2] = 0.7
assert np.isclose(tree.min(), 0.7)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 0.7)
assert np.isclose(tree.min(0, -1), 0.7)
assert np.isclose(tree.min(2, 4), 0.7)
assert np.isclose(tree.min(3, 4), 3.0)
tree[2] = 4.0
assert np.isclose(tree.min(), 1.0)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 1.0)
assert np.isclose(tree.min(0, -1), 1.0)
assert np.isclose(tree.min(2, 4), 3.0)
assert np.isclose(tree.min(2, 3), 4.0)
assert np.isclose(tree.min(2, -1), 4.0)
assert np.isclose(tree.min(3, 4), 3.0)
示例24
def __init__(self, size, alpha):
"""Create Prioritized Replay buffer.
Parameters
----------
size: int
Max number of transitions to store in the buffer. When the buffer
overflows the old memories are dropped.
alpha: float
how much prioritization is used
(0 - no prioritization, 1 - full prioritization)
See Also
--------
ReplayBuffer.__init__
"""
super(PrioritizedReplayBuffer, self).__init__(size)
assert alpha >= 0
self._alpha = alpha
it_capacity = 1
while it_capacity < size:
it_capacity *= 2
self._it_sum = SumSegmentTree(it_capacity)
self._it_min = MinSegmentTree(it_capacity)
self._max_priority = 1.0
示例25
def test_max_interval_tree():
tree = MinSegmentTree(4)
tree[0] = 1.0
tree[2] = 0.5
tree[3] = 3.0
assert np.isclose(tree.min(), 0.5)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 0.5)
assert np.isclose(tree.min(0, -1), 0.5)
assert np.isclose(tree.min(2, 4), 0.5)
assert np.isclose(tree.min(3, 4), 3.0)
tree[2] = 0.7
assert np.isclose(tree.min(), 0.7)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 0.7)
assert np.isclose(tree.min(0, -1), 0.7)
assert np.isclose(tree.min(2, 4), 0.7)
assert np.isclose(tree.min(3, 4), 3.0)
tree[2] = 4.0
assert np.isclose(tree.min(), 1.0)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 1.0)
assert np.isclose(tree.min(0, -1), 1.0)
assert np.isclose(tree.min(2, 4), 3.0)
assert np.isclose(tree.min(2, 3), 4.0)
assert np.isclose(tree.min(2, -1), 4.0)
assert np.isclose(tree.min(3, 4), 3.0)
示例26
def __init__(self, size, alpha):
"""Create Prioritized Replay buffer.
Parameters
----------
size: int
Max number of transitions to store in the buffer. When the buffer
overflows the old memories are dropped.
alpha: float
how much prioritization is used
(0 - no prioritization, 1 - full prioritization)
See Also
--------
ReplayBuffer.__init__
"""
super(PrioritizedReplayBuffer, self).__init__(size)
assert alpha >= 0
self._alpha = alpha
it_capacity = 1
while it_capacity < size:
it_capacity *= 2
self._it_sum = SumSegmentTree(it_capacity)
self._it_min = MinSegmentTree(it_capacity)
self._max_priority = 1.0
示例27
def test_max_interval_tree():
tree = MinSegmentTree(4)
tree[0] = 1.0
tree[2] = 0.5
tree[3] = 3.0
assert np.isclose(tree.min(), 0.5)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 0.5)
assert np.isclose(tree.min(0, -1), 0.5)
assert np.isclose(tree.min(2, 4), 0.5)
assert np.isclose(tree.min(3, 4), 3.0)
tree[2] = 0.7
assert np.isclose(tree.min(), 0.7)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 0.7)
assert np.isclose(tree.min(0, -1), 0.7)
assert np.isclose(tree.min(2, 4), 0.7)
assert np.isclose(tree.min(3, 4), 3.0)
tree[2] = 4.0
assert np.isclose(tree.min(), 1.0)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 1.0)
assert np.isclose(tree.min(0, -1), 1.0)
assert np.isclose(tree.min(2, 4), 3.0)
assert np.isclose(tree.min(2, 3), 4.0)
assert np.isclose(tree.min(2, -1), 4.0)
assert np.isclose(tree.min(3, 4), 3.0)
示例28
def __init__(self, size, alpha):
"""Create Prioritized Replay buffer.
Parameters
----------
size: int
Max number of transitions to store in the buffer. When the buffer
overflows the old memories are dropped.
alpha: float
how much prioritization is used
(0 - no prioritization, 1 - full prioritization)
See Also
--------
ReplayBuffer.__init__
"""
super(PrioritizedReplayBuffer, self).__init__(size)
assert alpha >= 0
self._alpha = alpha
it_capacity = 1
while it_capacity < size:
it_capacity *= 2
self._it_sum = SumSegmentTree(it_capacity)
self._it_min = MinSegmentTree(it_capacity)
self._max_priority = 1.0
示例29
def test_max_interval_tree():
tree = MinSegmentTree(4)
tree[0] = 1.0
tree[2] = 0.5
tree[3] = 3.0
assert np.isclose(tree.min(), 0.5)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 0.5)
assert np.isclose(tree.min(0, -1), 0.5)
assert np.isclose(tree.min(2, 4), 0.5)
assert np.isclose(tree.min(3, 4), 3.0)
tree[2] = 0.7
assert np.isclose(tree.min(), 0.7)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 0.7)
assert np.isclose(tree.min(0, -1), 0.7)
assert np.isclose(tree.min(2, 4), 0.7)
assert np.isclose(tree.min(3, 4), 3.0)
tree[2] = 4.0
assert np.isclose(tree.min(), 1.0)
assert np.isclose(tree.min(0, 2), 1.0)
assert np.isclose(tree.min(0, 3), 1.0)
assert np.isclose(tree.min(0, -1), 1.0)
assert np.isclose(tree.min(2, 4), 3.0)
assert np.isclose(tree.min(2, 3), 4.0)
assert np.isclose(tree.min(2, -1), 4.0)
assert np.isclose(tree.min(3, 4), 3.0)
示例30
def __init__(self, size, alpha):
super(PrioritizedReplayBuffer, self).__init__(size)
assert alpha > 0
self._alpha = alpha
it_capacity = 1
while it_capacity < size:
it_capacity *= 2
self._it_sum = SumSegmentTree(it_capacity)
self._it_min = MinSegmentTree(it_capacity)
self._max_priority = 1.0
