garage.torch.policies.context_conditioned_policy module¶
A policy used in training meta reinforcement learning algorithms.
It is used in PEARL (Probabilistic Embeddings for Actor-Critic Reinforcement Learning). The paper on PEARL can be found at https://arxiv.org/abs/1903.08254. Code is adapted from https://github.com/katerakelly/oyster.
-
class
ContextConditionedPolicy(latent_dim, context_encoder, policy, use_information_bottleneck, use_next_obs)[source]¶ Bases:
sphinx.ext.autodoc.importer._MockObjectA 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()[source]¶ 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)[source]¶ 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: - obs (torch.Tensor) –
-
get_action(obs)[source]¶ 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)[source]¶ 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.