reference/generated/torchrl.trainers.algorithms.configs.transforms.ClosedLoopMultiActionConfig

Run in Google Colab

Colab

Download Notebook

Notebook

View on GitHub

GitHub

torchrl.trainers.algorithms.configs.transforms.ClosedLoopMultiActionConfig

class torchrl.trainers.algorithms.configs.transforms.ClosedLoopMultiActionConfig(controller: Any = '???', steps: int = '???', decision_spec: Any = None, reward_aggregation: str = 'sum', exploration_type: InteractionType = InteractionType.DETERMINISTIC, no_grad: bool = True, dim: int = 1, stack_observations: bool = False, _target_: str = 'torchrl.envs.transforms.ClosedLoopMultiAction')

Hydra configuration for ClosedLoopMultiAction.

Install controller primers first, or override the target with ClosedLoopMultiAction.from_env and supply the environment to instantiate.