garage.torch.policies.discrete_cnn_policy¶
Discrete CNN Policy.
- class DiscreteCNNPolicy(env_spec, image_format, kernel_sizes, hidden_channels, strides, hidden_sizes=(32, 32), cnn_hidden_nonlinearity=torch.nn.ReLU, mlp_hidden_nonlinearity=torch.nn.ReLU, hidden_w_init=nn.init.xavier_uniform_, hidden_b_init=nn.init.zeros_, paddings=0, padding_mode='zeros', max_pool=False, pool_shape=None, pool_stride=1, output_nonlinearity=None, output_w_init=nn.init.xavier_uniform_, output_b_init=nn.init.zeros_, layer_normalization=False, name='DiscreteCNNPolicy')¶
Bases:
garage.torch.policies.stochastic_policy.StochasticPolicy
DiscreteCNNPolicy.
A policy that contains a CNN and a MLP to make prediction based on a discrete distribution.
- Parameters
env_spec (EnvSpec) – Environment specification.
image_format (str) – Either ‘NCHW’ or ‘NHWC’. Should match env_spec. Gym uses NHWC by default, but PyTorch uses NCHW by default.
kernel_sizes (tuple[int]) – Dimension of the conv filters. For example, (3, 5) means there are two convolutional layers. The filter for first layer is of dimension (3 x 3) and the second one is of dimension (5 x 5).
strides (tuple[int]) – The stride of the sliding window. For example, (1, 2) means there are two convolutional layers. The stride of the filter for first layer is 1 and that of the second layer is 2.
hidden_channels (tuple[int]) – Number of output channels for CNN. For example, (3, 32) means there are two convolutional layers. The filter for the first conv layer outputs 3 channels
hidden_sizes (list[int]) – Output dimension of dense layer(s) for the MLP for mean. For example, (32, 32) means the MLP consists of two hidden layers, each with 32 hidden units.
mlp_hidden_nonlinearity (callable) – Activation function for intermediate dense layer(s) in the MLP. It should return a torch.Tensor. Set it to None to maintain a linear activation.
cnn_hidden_nonlinearity (callable) – Activation function for intermediate CNN layer(s). It should return a torch.Tensor. Set it to None to maintain a linear activation.
hidden_w_init (callable) – Initializer function for the weight of intermediate dense layer(s). The function should return a torch.Tensor.
hidden_b_init (callable) – Initializer function for the bias of intermediate dense layer(s). The function should return a torch.Tensor.
paddings (tuple[int]) – Zero-padding added to both sides of the input
padding_mode (str) – The type of padding algorithm to use, either ‘SAME’ or ‘VALID’.
max_pool (bool) – Bool for using max-pooling or not.
pool_shape (tuple[int]) – Dimension of the pooling layer(s). For example, (2, 2) means that all the pooling layers have shape (2, 2).
pool_stride (tuple[int]) – The strides of the pooling layer(s). For example, (2, 2) means that all the pooling layers have strides (2, 2).
output_nonlinearity (callable) – Activation function for output dense layer. It should return a torch.Tensor. Set it to None to maintain a linear activation.
output_w_init (callable) – Initializer function for the weight of output dense layer(s). The function should return a torch.Tensor.
output_b_init (callable) – Initializer function for the bias of output dense layer(s). The function should return a torch.Tensor.
layer_normalization (bool) – Bool for using layer normalization or not.
name (str) – Name of policy.
- property env_spec¶
Policy environment specification.
- Returns
Environment specification.
- Return type
- property observation_space¶
Observation space.
- Returns
The observation space of the environment.
- Return type
akro.Space
- property action_space¶
Action space.
- Returns
The action space of the environment.
- Return type
akro.Space
- forward(observations)¶
Compute the action distributions from the observations.
- Parameters
observations (torch.Tensor) – Batch of observations of shape \((N, O)\). Observations should be flattened even if they are images as the underlying Q network handles unflattening.
- Returns
Batch distribution of actions. dict[str, torch.Tensor]: Additional agent_info, as torch Tensors.
Do not need to be detached, and can be on any device.
- Return type
torch.distributions.Distribution
- get_action(observation)¶
Get a single action given an observation.
- Parameters
observation (np.ndarray) – Observation from the environment. Shape is \(env_spec.observation_space\).
- Returns
- np.ndarray: Predicted action. Shape is
\(env_spec.action_space\).
- dict:
np.ndarray[float]: Mean of the distribution
- np.ndarray[float]: Standard deviation of logarithmic
values of the distribution.
- Return type
- get_actions(observations)¶
Get actions given observations.
- Parameters
observations (np.ndarray) – Observations from the environment. Shape is \(batch_dim \bullet env_spec.observation_space\).
- Returns
- np.ndarray: Predicted actions.
\(batch_dim \bullet env_spec.action_space\).
- dict:
np.ndarray[float]: Mean of the distribution.
- np.ndarray[float]: Standard deviation of logarithmic
values of the distribution.
- Return type
- get_param_values()¶
Get the parameters to the policy.
This method is included to ensure consistency with TF policies.
- Returns
The parameters (in the form of the state dictionary).
- Return type
- set_param_values(state_dict)¶
Set the parameters to the policy.
This method is included to ensure consistency with TF policies.
- Parameters
state_dict (dict) – State dictionary.
- reset(do_resets=None)¶
Reset the policy.
This is effective only to recurrent policies.
do_resets is an array of boolean indicating which internal states to be reset. The length of do_resets should be equal to the length of inputs, i.e. batch size.
- Parameters
do_resets (numpy.ndarray) – Bool array indicating which states to be reset.