ray.rllib.algorithms.algorithm_config.AlgorithmConfig.build_learner#

AlgorithmConfig.build_learner(*, env: Any | gymnasium.Env | None = None, spaces: Dict[str, Tuple[gymnasium.Space, gymnasium.Space]] | None = None) → Learner[source]#

Builds and returns a new Learner object based on settings in self.

This Learner object will already have its build() method called, meaning its RLModule will already be constructed.

Parameters:

  • env – An optional EnvType object (e.g. a gym.Env) useful for extracting space information for the to-be-constructed RLModule inside the Learner. Note that if RLlib cannot infer any space information either from this env arg, from the optional spaces arg or from self, the Learner cannot be created.

  • spaces – An optional dict mapping ModuleIDs to (observation-space, action-space)-tuples for the to-be-constructed RLModule inside the Learner. Note that if RLlib cannot infer any space information either from this spces arg, from the optional env arg or from self, the Learner cannot be created.

Returns:

The newly created (and already built) Learner object.