def true_fn():
batch_size = 1
req = force_tuple(
action_dist.required_model_output_shape(
self.action_space, getattr(self.model, "model_config",
None)))
# Add a batch dimension?
if len(action_dist.inputs.shape) == len(req) + 1:
batch_size = tf.shape(action_dist.inputs)[0]
# Function to produce random samples from primitive space
# components: (Multi)Discrete or Box.
def random_component(component):
if isinstance(component, Discrete):
return tf.random.uniform(
shape=(batch_size, ) + component.shape,
maxval=component.n,
dtype=component.dtype)
elif isinstance(component, MultiDiscrete):
return tf.concat(
[
tf.random.uniform(
shape=(batch_size, 1),
maxval=n,
dtype=component.dtype) for n in component.nvec
],
axis=1)
elif isinstance(component, Box):
if component.bounded_above.all() and \
component.bounded_below.all():
if component.dtype.name.startswith("int"):
return tf.random.uniform(
shape=(batch_size, ) + component.shape,
minval=component.low.flat[0],
maxval=component.high.flat[0],
dtype=component.dtype)
else:
return tf.random.uniform(
shape=(batch_size, ) + component.shape,
minval=component.low,
maxval=component.high,
dtype=component.dtype)
else:
return tf.random.normal(
shape=(batch_size, ) + component.shape,
dtype=component.dtype)
else:
assert isinstance(component, Simplex), \
"Unsupported distribution component '{}' for random " \
"sampling!".format(component)
return tf.nn.softmax(
tf.random.uniform(
shape=(batch_size, ) + component.shape,
minval=0.0,
maxval=1.0,
dtype=component.dtype))
actions = tree.map_structure(random_component,
self.action_space_struct)
return actions
def get_torch_exploration_action(self, action_dist, explore):
if explore:
# Unsqueeze will be unnecessary, once we support batch/time-aware
# Spaces.
a = self.action_space.sample()
req = force_tuple(
action_dist.required_model_output_shape(
self.action_space, self.model.model_config))
# Add a batch dimension.
if len(action_dist.inputs.shape) == len(req) + 1:
a = np.expand_dims(a, 0)
action = torch.from_numpy(a).to(self.device)
else:
action = action_dist.deterministic_sample()
logp = torch.zeros(
(action.size()[0], ), dtype=torch.float32, device=self.device)
return action, logp
def get_torch_exploration_action(self, action_dist, explore):
if explore:
req = force_tuple(
action_dist.required_model_output_shape(
self.action_space, self.model.model_config))
# Add a batch dimension?
if len(action_dist.inputs.shape) == len(req) + 1:
batch_size = action_dist.inputs.shape[0]
a = np.stack(
[self.action_space.sample() for _ in range(batch_size)])
else:
a = self.action_space.sample()
# Convert action to torch tensor.
action = torch.from_numpy(a).to(self.device)
else:
action = action_dist.deterministic_sample()
logp = torch.zeros((action.size()[0], ),
dtype=torch.float32,
device=self.device)
return action, logp
def true_fn():
batch_size = 1
req = force_tuple(
action_dist.required_model_output_shape(
self.action_space, self.model.model_config))
# Add a batch dimension?
if len(action_dist.inputs.shape) == len(req) + 1:
batch_size = tf.shape(action_dist.inputs)[0]
# Function to produce random samples from primitive space
# components: (Multi)Discrete or Box.
def random_component(component):
if isinstance(component, Discrete):
return tf.random.uniform(shape=(batch_size, ) +
component.shape,
maxval=component.n,
dtype=component.dtype)
elif isinstance(component, MultiDiscrete):
return tf.concat([
tf.random.uniform(shape=(batch_size, 1),
maxval=n,
dtype=component.dtype)
for n in component.nvec
],
axis=1)
elif isinstance(component, Box):
if component.bounded_above.all() and \
component.bounded_below.all():
return tf.random.uniform(shape=(batch_size, ) +
component.shape,
minval=component.low,
maxval=component.high,
dtype=component.dtype)
else:
return tf.random.normal(shape=(batch_size, ) +
component.shape,
dtype=component.dtype)
actions = tree.map_structure(random_component,
self.action_space_struct)
return actions
