garage.torch.policies package

PyTorch Policies.

class DeterministicMLPPolicy(env_spec, name='DeterministicMLPPolicy', **kwargs)

Bases: garage.torch.policies.policy.Policy

Implements a deterministic policy network.

The policy network selects action based on the state of the environment. It uses a PyTorch neural network module to fit the function of pi(s).

forward(observations)

Compute actions from the observations.

Parameters:observations (torch.Tensor) – Batch of observations on default torch device. Returns:Batch of actions. Return type:torch.Tensor

get_action(observation)

Get a single action given an observation.

Parameters:observation (np.ndarray) – Observation from the environment. Returns:

• np.ndarray: Predicted action.

• dict:

  • list[float]: Mean of the distribution

  • list[float]: Log of standard deviation of the

    distribution

Return type:tuple

get_actions(observations)

Get actions given observations.

Parameters:observations (np.ndarray) – Observations from the environment. Returns:

• np.ndarray: Predicted actions.

• dict:

  • list[float]: Mean of the distribution

  • list[float]: Log of standard deviation of the

    distribution

Return type:tuple

class GaussianMLPPolicy(env_spec, hidden_sizes=(32, 32), hidden_nonlinearity=<sphinx.ext.autodoc.importer._MockObject object>, hidden_w_init=<sphinx.ext.autodoc.importer._MockObject object>, hidden_b_init=<sphinx.ext.autodoc.importer._MockObject object>, output_nonlinearity=None, output_w_init=<sphinx.ext.autodoc.importer._MockObject object>, output_b_init=<sphinx.ext.autodoc.importer._MockObject object>, learn_std=True, init_std=1.0, min_std=1e-06, max_std=None, std_parameterization='exp', layer_normalization=False, name='GaussianMLPPolicy')

Bases: garage.torch.policies.stochastic_policy.StochasticPolicy

MLP whose outputs are fed into a Normal distribution..

A policy that contains a MLP to make prediction based on a gaussian distribution.

Parameters:

• env_spec (garage.envs.env_spec.EnvSpec) – Environment specification.
• 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.
• hidden_nonlinearity (callable) – Activation function for intermediate dense 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.
• 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.
• learn_std (bool) – Is std trainable.
• init_std (float) – Initial value for std. (plain value - not log or exponentiated).
• min_std (float) – Minimum value for std.
• max_std (float) – Maximum value for std.
• std_parameterization (str) –

  How the std should be parametrized. There are two options: - exp: the logarithm of the std will be stored, and applied a

  exponential transformation

  • softplus: the std will be computed as log(1+exp(x))
• layer_normalization (bool) – Bool for using layer normalization or not.
• name (str) – Name of policy.

forward(observations)

Compute the action distributions from the observations.

Parameters:observations (torch.Tensor) – Batch of observations on default torch device. Returns:Batch distribution of actions. dict[str, torch.Tensor]: Additional agent_info, as torch Tensors Return type:torch.distributions.Distribution

class Policy(env_spec, name)

Bases: sphinx.ext.autodoc.importer._MockObject, abc.ABC

Policy base class.

Parameters:

• env_spec (garage.envs.env_spec.EnvSpec) – Environment specification.
• name (str) – Name of policy.

action_space

The action space for the environment.

Returns:Action space. Return type:akro.Space

get_action(observation)

Get a single action given an observation.

Parameters:observation (torch.Tensor) – Observation from the environment. Returns:

• torch.Tensor: Predicted action.

• dict:

  • list[float]: Mean of the distribution

  • list[float]: Log of standard deviation of the

    distribution

Return type:tuple

get_actions(observations)

Get actions given observations.

Parameters:observations (torch.Tensor) – Observations from the environment. Returns:

• torch.Tensor: Predicted actions.

• dict:

  • list[float]: Mean of the distribution

  • list[float]: Log of standard deviation of the

    distribution

Return type:tuple

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:dict

name

Name of policy.

Returns:Name of policy Return type:str

observation_space

The observation space for the environment.

Returns:Observation space. Return type:akro.Space

reset(dones=None)

Reset the environment.

Parameters:dones (numpy.ndarray) – Reset values

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.

class TanhGaussianMLPPolicy(env_spec, hidden_sizes=(32, 32), hidden_nonlinearity=<sphinx.ext.autodoc.importer._MockObject object>, hidden_w_init=<sphinx.ext.autodoc.importer._MockObject object>, hidden_b_init=<sphinx.ext.autodoc.importer._MockObject object>, output_nonlinearity=None, output_w_init=<sphinx.ext.autodoc.importer._MockObject object>, output_b_init=<sphinx.ext.autodoc.importer._MockObject object>, init_std=1.0, min_std=2.061153622438558e-09, max_std=7.38905609893065, std_parameterization='exp', layer_normalization=False)

Bases: garage.torch.policies.stochastic_policy.StochasticPolicy

Multiheaded MLP whose outputs are fed into a TanhNormal distribution.

A policy that contains a MLP to make prediction based on a gaussian distribution with a tanh transformation.

Parameters:

• env_spec (garage.envs.env_spec.EnvSpec) – Environment specification.
• 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.
• hidden_nonlinearity (callable) – Activation function for intermediate dense 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.
• 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.
• init_std (float) – Initial value for std. (plain value - not log or exponentiated).
• min_std (float) – If not None, the std is at least the value of min_std, to avoid numerical issues (plain value - not log or exponentiated).
• max_std (float) – If not None, the std is at most the value of max_std, to avoid numerical issues (plain value - not log or exponentiated).
• std_parameterization (str) –

  How the std should be parametrized. There are two options: - exp: the logarithm of the std will be stored, and applied a

  exponential transformation

  • softplus: the std will be computed as log(1+exp(x))
• layer_normalization (bool) – Bool for using layer normalization or not.

forward(observations)

Compute the action distributions from the observations.

Parameters:observations (torch.Tensor) – Batch of observations on default torch device. Returns:Batch distribution of actions. dict[str, torch.Tensor]: Additional agent_info, as torch Tensors Return type:torch.distributions.Distribution

class ContextConditionedPolicy(latent_dim, context_encoder, policy, use_information_bottleneck, use_next_obs)

Bases: sphinx.ext.autodoc.importer._MockObject

A policy that outputs actions based on observation and latent context.

In PEARL, policies are conditioned on current state and a latent context (adaptation data) variable Z. This inference network estimates the posterior probability of z given past transitions. It uses context information stored in the encoder to infer the probabilistic value of z and samples from a policy conditioned on z.

Parameters:

• latent_dim (int) – Latent context variable dimension.
• context_encoder (garage.torch.embeddings.ContextEncoder) – Recurrent or permutation-invariant context encoder.
• policy (garage.torch.policies.Policy) – Policy used to train the network.
• use_information_bottleneck (bool) – True if latent context is not deterministic; false otherwise.
• use_next_obs (bool) – True if next observation is used in context for distinguishing tasks; false otherwise.

compute_kl_div()

Compute \(KL(q(z|c) \| p(z))\).

Returns:\(KL(q(z|c) \| p(z))\). Return type:float

context

Return context.

Returns:

Context values, with shape \((X, N, C)\).

X is the number of tasks. N is batch size. C is the combined size of observation, action, reward, and next observation if next observation is used in context. Otherwise, C is the combined size of observation, action, and reward.

Return type:torch.Tensor

forward(obs, context)

Given observations and context, get actions and probs from policy.

Parameters:

• obs (torch.Tensor) –

  Observation values, with shape \((X, N, O)\). X is the number of tasks. N is batch size. O

  is the size of the flattened observation space.

• context (torch.Tensor) – Context values, with shape \((X, N, C)\). X is the number of tasks. N is batch size. C is the combined size of observation, action, reward, and next observation if next observation is used in context. Otherwise, C is the combined size of observation, action, and reward.

Returns:

• torch.Tensor: Predicted action values.

  • np.ndarray: Mean of distribution.
  • np.ndarray: Log std of distribution.
  • torch.Tensor: Log likelihood of distribution.

  • torch.Tensor: Sampled values from distribution before

    applying tanh transformation.

torch.Tensor: z values, with shape \((N, L)\). N is batch size.

L is the latent dimension.

Return type:

tuple

get_action(obs)

Sample action from the policy, conditioned on the task embedding.

Parameters:obs (torch.Tensor) – Observation values, with shape \((1, O)\). O is the size of the flattened observation space. Returns:

Output action value, with shape \((1, A)\).

A is the size of the flattened action space.

dict:

• np.ndarray[float]: Mean of the distribution.

• np.ndarray[float]: Standard deviation of logarithmic values

  of the distribution.

Return type:torch.Tensor

infer_posterior(context)

Compute \(q(z \| c)\) as a function of input context and sample new z.

Parameters:context (torch.Tensor) – Context values, with shape \((X, N, C)\). X is the number of tasks. N is batch size. C is the combined size of observation, action, reward, and next observation if next observation is used in context. Otherwise, C is the combined size of observation, action, and reward.

networks

Return context_encoder and policy.

Returns:Encoder and policy networks. Return type:list

reset_belief(num_tasks=1)

Reset \(q(z \| c)\) to the prior and sample a new z from the prior.

Parameters:num_tasks (int) – Number of tasks.

sample_from_belief()

Sample z using distributions from current means and variances.

update_context(timestep)

Append single transition to the current context.

Parameters:timestep (garage._dtypes.TimeStep) – Timestep containing transition information to be added to context.

Submodules

• garage.torch.policies.context_conditioned_policy module
• garage.torch.policies.deterministic_mlp_policy module
• garage.torch.policies.gaussian_mlp_policy module
• garage.torch.policies.policy module
• garage.torch.policies.stochastic_policy module
• garage.torch.policies.tanh_gaussian_mlp_policy module