metarl.torch.policies.gaussian_mlp_policy module

GaussianMLPPolicy.

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')[source]

Bases: metarl.torch.policies.policy.Policy, metarl.torch.modules.gaussian_mlp_module.GaussianMLPModule

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 (metarl.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.
entropy(observation)[source]

Get entropy given observations.

Parameters:observation (torch.Tensor) – Observation from the environment. Shape is \(env_spec.observation_space\).
Returns:
Calculated entropy values given observation.
Shape is \(1\).
Return type:torch.Tensor
get_action(observation)[source]

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:tuple
get_actions(observations)[source]

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:tuple
log_likelihood(observation, action)[source]

Compute log likelihood given observations and action.

Parameters:
  • observation (torch.Tensor) – Observation from the environment. Shape is \(env_spec.observation_space\).
  • action (torch.Tensor) – Predicted action. Shape is \(env_spec.action_space\).
Returns:

Calculated log likelihood value of the action given

observation. Shape is \(1\).
Return type:

torch.Tensor
reset(dones=None)[source]

Reset the environment.

Parameters:dones (numpy.ndarray) – Reset values
vectorized

Vectorized or not.

Returns:flag for vectorized
Return type:bool