def __init__(self, obs_space, num_outputs, options):
TorchModel.__init__(self, obs_space, num_outputs, options)
hiddens = options.get("fcnet_hiddens")
activation = _get_activation_fn(options.get("fcnet_activation"))
logger.debug("Constructing fcnet {} {}".format(hiddens, activation))
layers = []
last_layer_size = np.product(obs_space.shape)
for size in hiddens:
layers.append(
SlimFC(
in_size=last_layer_size,
out_size=size,
initializer=normc_initializer(1.0),
activation_fn=activation))
last_layer_size = size
self._hidden_layers = nn.Sequential(*layers)
self._logits = SlimFC(
in_size=last_layer_size,
out_size=num_outputs,
initializer=normc_initializer(0.01),
activation_fn=None)
self._value_branch = SlimFC(
in_size=last_layer_size,
out_size=1,
initializer=normc_initializer(1.0),
activation_fn=None)
def __init__(self, obs_space, num_outputs, options):
TorchModel.__init__(self, obs_space, num_outputs, options)
hiddens = options.get("fcnet_hiddens")
activation = _get_activation_fn(options.get("fcnet_activation"))
logger.debug("Constructing fcnet {} {}".format(hiddens, activation))
layers = []
last_layer_size = np.product(obs_space.shape)
for size in hiddens:
layers.append(
SlimFC(in_size=last_layer_size,
out_size=size,
initializer=normc_initializer(1.0),
activation_fn=activation))
last_layer_size = size
self._hidden_layers = nn.Sequential(*layers)
self._logits = SlimFC(in_size=last_layer_size,
out_size=num_outputs,
initializer=normc_initializer(0.01),
activation_fn=None)
self._value_branch = SlimFC(in_size=last_layer_size,
out_size=1,
initializer=normc_initializer(1.0),
activation_fn=None)
def __init__(self, obs_space, num_outputs, options):
TorchModel.__init__(self, obs_space, num_outputs, options)
filters = options.get("conv_filters")
if not filters:
filters = _get_filter_config(obs_space.shape)
layers = []
(w, h, in_channels) = obs_space.shape
in_size = [w, h]
for out_channels, kernel, stride in filters[:-1]:
padding, out_size = valid_padding(in_size, kernel,
[stride, stride])
layers.append(
SlimConv2d(in_channels, out_channels, kernel, stride, padding))
in_channels = out_channels
in_size = out_size
out_channels, kernel, stride = filters[-1]
layers.append(
SlimConv2d(in_channels, out_channels, kernel, stride, None))
self._convs = nn.Sequential(*layers)
self._logits = SlimFC(out_channels,
num_outputs,
initializer=nn.init.xavier_uniform_)
self._value_branch = SlimFC(out_channels,
1,
initializer=normc_initializer())
def __init__(self, obs_space, num_outputs, options):
TorchModel.__init__(self, obs_space, num_outputs, options)
filters = options.get("conv_filters")
if not filters:
filters = _get_filter_config(obs_space.shape)
layers = []
(w, h, in_channels) = obs_space.shape
in_size = [w, h]
for out_channels, kernel, stride in filters[:-1]:
padding, out_size = valid_padding(in_size, kernel,
[stride, stride])
layers.append(
SlimConv2d(in_channels, out_channels, kernel, stride, padding))
in_channels = out_channels
in_size = out_size
out_channels, kernel, stride = filters[-1]
layers.append(
SlimConv2d(in_channels, out_channels, kernel, stride, None))
self._convs = nn.Sequential(*layers)
self._logits = SlimFC(
out_channels, num_outputs, initializer=nn.init.xavier_uniform_)
self._value_branch = SlimFC(
out_channels, 1, initializer=normc_initializer())
def __init__(self, obs_space, num_outputs, options):
TorchModel.__init__(self, obs_space, num_outputs, options)
self.obs_size = _get_size(obs_space)
self.rnn_hidden_dim = options["lstm_cell_size"]
self.fc1 = nn.Linear(self.obs_size, self.rnn_hidden_dim)
self.rnn = nn.GRUCell(self.rnn_hidden_dim, self.rnn_hidden_dim)
self.fc2 = nn.Linear(self.rnn_hidden_dim, num_outputs)
def __init__(self, obs_space, num_outputs, options):
TorchModel.__init__(self, obs_space, num_outputs, options)
self.obs_size = _get_size(obs_space)
self.rnn_hidden_dim = options["lstm_cell_size"]
self.fc1 = nn.Linear(self.obs_size, self.rnn_hidden_dim)
self.rnn = nn.GRUCell(self.rnn_hidden_dim, self.rnn_hidden_dim)
self.fc2 = nn.Linear(self.rnn_hidden_dim, num_outputs)
def __init__(self, obs_space, num_outputs, options):
TorchModel.__init__(self, obs_space, num_outputs, options)
self.fc = FullyConnectedNetwork(
obs_space.original_space.spaces["sensors"].spaces["position"],
num_outputs, options)
def __init__(self, obs_space, num_outputs, options):
TorchModel.__init__(self, obs_space, num_outputs, options)
self.fc = FullyConnectedNetwork(
obs_space.original_space.spaces["sensors"].spaces["position"],
num_outputs, options)