BCConfig#
- class ray.rllib.algorithms.bc.bc.BCConfig(algo_class=None)[source]#
Bases:
MARWILConfigDefines a configuration class from which a new BC Algorithm can be built
Examples
>>> from pathlib import Path >>> import gymnasium as gym >>> from ray.rllib.algorithms.bc import BCConfig >>> # Get the path to the CartPole data in the rllib folder. >>> base_path = Path(__file__).parents[2] >>> data_path = base_path / "offline/tests/data/cartpole/cartpole-v1_large" >>> config = BCConfig().training(lr=0.00001, gamma=0.99) >>> # Set the observation and action spaces of the data. >>> env = gym.make("CartPole-v1") >>> config = config.environment( ... observation_space=env.observation_space, ... action_space=env.action_space, ... ) >>> config = config.offline_data( ... input_=[data_path.as_posix()], ... # Run exactly one update per training iteration. ... dataset_num_iters_per_learner=1, ... ) >>> # Build an Algorithm object from the config and run 1 training iteration. >>> algo = config.build() >>> _ = algo.train()
>>> from ray.rllib.algorithms.bc import BCConfig >>> from ray import tune >>> config = BCConfig() >>> # Print out some default values. >>> print(config.beta) 0.0 >>> # Update the config object. >>> _ = config.training(lr=tune.grid_search([0.001, 0.0001])) >>> # Set the config object's data path. >>> _ = config.offline_data( ... input_=[data_path.as_posix()], ... dataset_num_iters_per_learner=1, ... ) >>> # Set the observation and action spaces of the data. >>> _ = config.environment( ... observation_space=env.observation_space, ... action_space=env.action_space, ... ) >>> # Use to_dict() to get the old-style python config dict >>> # when running with tune. >>> print("[ignore]"); results = tune.Tuner( ... "BC", ... param_space=config.to_dict(), ... # Run one trial at a time so each trial's offline data ... # pipeline can get the CPUs it needs. ... tune_config=tune.TuneConfig(max_concurrent_trials=1), ... run_config=tune.RunConfig(stop={"training_iteration": 1}), ... ).fit() [ignore]... >>> results.num_errors 0
- get_default_rl_module_spec() RLModuleSpec | MultiRLModuleSpec[source]#
Returns the RLModule spec to use for this algorithm.
Override this method in the subclass to return the RLModule spec, given the input framework.
- Returns:
The RLModuleSpec (or MultiRLModuleSpec) to use for this algorithm’s RLModule.
- Return type: