garage.torch.policies.context_conditioned_policy
¶
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)¶
Bases:
torch.nn.Module
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.
- property networks¶
Return context_encoder and policy.
- Returns
Encoder and policy networks.
- Return type
- property 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
- 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.
- 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.
- 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
- 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