ConcatModelBuilder¶
-
class
maze.perception.builders.concat.ConcatModelBuilder(modality_config: Dict[str, Union[str, Dict[str, Any]]], observation_modality_mapping: Dict[str, str])¶ A model builder that first processes individual observations, concatenates the resulting latent spaces and then processes this concatenated output to action and value outputs.
Each input observation is first processed with the specified perception block. The required feature dimensionality after this step is 1D! In a next step the latent representations of the previous step are concatenated along the last dimension and once more processed with a
DenseBlock.- Param
modality_config: dictionary mapping perception modalities to blocks and block config parameters.
- Parameters
observation_modality_mapping – A mapping of observation keys to perception modalities.
-
from_observation_space(observation_space: gym.spaces.Dict) → maze.perception.blocks.inference.InferenceBlock¶ implementation of
BaseModelBuilderinterface