def __init__(self, limit, **kwargs):
super(EpisodeParameterMemory, self).__init__(**kwargs)
self.limit = limit
self.params = RingBuffer(limit)
self.intermediate_rewards = []
self.total_rewards = RingBuffer(limit)
class EpisodeParameterMemory(Memory):
def __init__(self, limit, **kwargs):
super(EpisodeParameterMemory, self).__init__(**kwargs)
self.limit = limit
self.params = RingBuffer(limit)
self.intermediate_rewards = []
self.total_rewards = RingBuffer(limit)
def sample(self, batch_size, batch_idxs=None):
if batch_idxs is None:
batch_idxs = sample_batch_indexes(0,
self.nb_entries,
size=batch_size)
assert len(batch_idxs) == batch_size
batch_params = []
batch_total_rewards = []
for idx in batch_idxs:
batch_params.append(self.params[idx])
batch_total_rewards.append(self.total_rewards[idx])
return batch_params, batch_total_rewards
def append(self, observation, action, reward, terminal, training=True):
super(EpisodeParameterMemory, self).append(observation,
action,
reward,
terminal,
training=training)
if training:
self.intermediate_rewards.append(reward)
def finalize_episode(self, params):
total_reward = sum(self.intermediate_rewards)
self.total_rewards.append(total_reward)
self.params.append(params)
self.intermediate_rewards = []
@property
def nb_entries(self):
return len(self.total_rewards)
def get_config(self):
config = super(SequentialMemory, self).get_config()
config['limit'] = self.limit
return config
def __init__(self, limit, **kwargs):
super(SequentialMemory, self).__init__(**kwargs)
self.limit = limit
# Do not use deque to implement the memory. This data structure may seem convenient but
# it is way too slow on random access. Instead, we use our own ring buffer implementation.
self.actions = RingBuffer(limit)
self.rewards = RingBuffer(limit)
self.terminals = RingBuffer(limit)
self.observations = RingBuffer(limit)
class SequentialMemory(Memory):
def __init__(self, limit, **kwargs):
super(SequentialMemory, self).__init__(**kwargs)
self.limit = limit
# Do not use deque to implement the memory. This data structure may seem convenient but
# it is way too slow on random access. Instead, we use our own ring buffer implementation.
self.actions = RingBuffer(limit)
self.rewards = RingBuffer(limit)
self.terminals = RingBuffer(limit)
self.observations = RingBuffer(limit)
def sample(self, batch_size, batch_idxs=None):
if batch_idxs is None:
# Draw random indexes such that we have at least a single entry before each
# index.
batch_idxs = sample_batch_indexes(0,
self.nb_entries - 1,
size=batch_size)
batch_idxs = np.array(batch_idxs) + 1
assert np.min(batch_idxs) >= 1
assert np.max(batch_idxs) < self.nb_entries
assert len(batch_idxs) == batch_size
# Create experiences
experiences = []
for idx in batch_idxs:
terminal0 = self.terminals[idx - 2] if idx >= 2 else False
while terminal0:
# Skip this transition because the environment was reset here. Select a new, random
# transition and use this instead. This may cause the batch to contain the same
# transition twice.
idx = sample_batch_indexes(1, self.nb_entries, size=1)[0]
terminal0 = self.terminals[idx - 2] if idx >= 2 else False
assert 1 <= idx < self.nb_entries
# This code is slightly complicated by the fact that subsequent observations might be
# from different episodes. We ensure that an experience never spans multiple episodes.
# This is probably not that important in practice but it seems cleaner.
state0 = [self.observations[idx - 1]]
for offset in range(0, self.window_length - 1):
current_idx = idx - 2 - offset
current_terminal = self.terminals[
current_idx - 1] if current_idx - 1 > 0 else False
if current_idx < 0 or (not self.ignore_episode_boundaries
and current_terminal):
# The previously handled observation was terminal, don't add the current one.
# Otherwise we would leak into a different episode.
break
state0.insert(0, self.observations[current_idx])
while len(state0) < self.window_length:
state0.insert(0, zeroed_observation(state0[0]))
action = self.actions[idx - 1]
reward = self.rewards[idx - 1]
terminal1 = self.terminals[idx - 1]
# Okay, now we need to create the follow-up state. This is state0 shifted on timestep
# to the right. Again, we need to be careful to not include an observation from the next
# episode if the last state is terminal.
state1 = [np.copy(x) for x in state0[1:]]
state1.append(self.observations[idx])
assert len(state0) == self.window_length
assert len(state1) == len(state0)
experiences.append(
Experience(state0=state0,
action=action,
reward=reward,
state1=state1,
terminal1=terminal1))
assert len(experiences) == batch_size
return experiences
def append(self, observation, action, reward, terminal, training=True):
super(SequentialMemory, self).append(observation,
action,
reward,
terminal,
training=training)
# This needs to be understood as follows: in `observation`, take `action`, obtain `reward`
# and weather the next state is `terminal` or not.
if training:
self.observations.append(observation)
self.actions.append(action)
self.rewards.append(reward)
self.terminals.append(terminal)
@property
def nb_entries(self):
return len(self.observations)
def get_config(self):
config = super(SequentialMemory, self).get_config()
config['limit'] = self.limit
return config