ray.rllib.core.rl_module.rl_module.RLModuleConfig#

class ray.rllib.core.rl_module.rl_module.RLModuleConfig(observation_space: <MagicMock name='mock.Space' id='140096994818384'> = None, action_space: <MagicMock name='mock.Space' id='140096994818384'> = None, model_config_dict: Dict[str, Any] = None, catalog_class: Type[Catalog] = None)[source]#

Bases: object

A utility config class to make it constructing RLModules easier.

Parameters

  • observation_space – The observation space of the RLModule. This may differ from the observation space of the environment. For example, a discrete observation space of an environment, would usually correspond to a one-hot encoded observation space of the RLModule because of preprocessing.

  • action_space – The action space of the RLModule.

  • model_config_dict – The model config dict to use.

  • catalog_class – The Catalog class to use.

Methods

from_dict(d)

Creates a config from a serialized representation.

get_catalog()

Returns the catalog for this config.

to_dict()

Returns a serialized representation of the config.

Attributes

action_space

catalog_class

model_config_dict

observation_space