ray.rllib.offline.offline_env_runner.OfflineSingleAgentEnvRunner#

class ray.rllib.offline.offline_env_runner.OfflineSingleAgentEnvRunner(*, config: AlgorithmConfig, **kwargs)[source]#

The environment runner to record the single agent case.

PublicAPI (alpha): This API is in alpha and may change before becoming stable.

Methods

`apply`	Calls the given function with this Actor instance.
`assert_healthy`	Checks that self.__init__() has been completed properly.
`from_checkpoint`	Creates a new Checkpointable instance from the given location and returns it.
`make_env`	Creates a vectorized gymnasium env and stores it in `self.env`.
`ping`	Ping the actor.
`restore_from_path`	Restores the state of the implementing class from the given path.
`sample`	Samples from environments and writes data to disk.
`save_to_path`	Saves the state of the implementing class (or `state`) to `path`.
`stop`	Writes the reamining samples to disk

Attributes