`garage.np.embeddings.encoder`¶

Base class for context encoder.

class Encoder[source]¶

Bases: abc.ABC

Inheritance diagram of garage.np.embeddings.encoder.Encoder

Base class of context encoders for training meta-RL algorithms.

abstract property spec¶

Input and output space.

Type: garage.InOutSpec

abstract property input_dim¶

Dimension of the encoder input.

Type: int

abstract property output_dim¶

Dimension of the encoder output (embedding).

Type: int

reset(do_resets=None)[source]¶

Reset the encoder.

This is effective only to recurrent encoder. do_resets is effective only to vectoried encoder.

For a vectorized encoder, 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.

Parameters: do_resets (numpy.ndarray) – Bool array indicating which states to be reset.

class StochasticEncoder[source]¶

Bases: Encoder

Inheritance diagram of garage.np.embeddings.encoder.StochasticEncoder

An stochastic context encoders.

An stochastic encoder maps an input to a distribution, but not a deterministic vector.

abstract property distribution¶

Embedding distribution.

Type: object