ray.rllib.algorithms.algorithm_config.AlgorithmConfig

class ray.rllib.algorithms.algorithm_config.AlgorithmConfig(algo_class=None)

Bases: ray.tune.tune._Config

A RLlib AlgorithmConfig builds an RLlib Algorithm from a given configuration.

Example

>>> from ray.rllib.algorithms.algorithm_config import AlgorithmConfig
>>> from ray.rllib.algorithms.callbacks import MemoryTrackingCallbacks
>>> # Construct a generic config object, specifying values within different
>>> # sub-categories, e.g. "training".
>>> config = AlgorithmConfig().training(gamma=0.9, lr=0.01)  
...     .environment(env="CartPole-v1")
...     .resources(num_gpus=0)
...     .rollouts(num_rollout_workers=4)
...     .callbacks(MemoryTrackingCallbacks)
>>> # A config object can be used to construct the respective Algorithm.
>>> rllib_algo = config.build()  

Example

>>> from ray.rllib.algorithms.algorithm_config import AlgorithmConfig
>>> from ray import tune
>>> # In combination with a tune.grid_search:
>>> config = AlgorithmConfig()
>>> config.training(lr=tune.grid_search([0.01, 0.001])) 
>>> # Use `to_dict()` method to get the legacy plain python config dict
>>> # for usage with `tune.Tuner().fit()`.
>>> tune.Tuner(  
...     "[registered Algorithm class]", param_space=config.to_dict()
...     ).fit()

Methods

build([env, logger_creator, use_copy])	Builds an Algorithm from this AlgorithmConfig (or a copy thereof).
callbacks(callbacks_class)	Sets the callbacks configuration.
checkpointing([export_native_model_files, ...])	Sets the config's checkpointing settings.
copy([copy_frozen])	Creates a deep copy of this config and (un)freezes if necessary.
debugging(*[, logger_creator, ...])	Sets the config's debugging settings.
environment([env, env_config, ...])	Sets the config's RL-environment settings.
evaluation(*[, evaluation_interval, ...])	Sets the config's evaluation settings.
experimental(*[, ...])	Sets the config's experimental settings.
exploration(*[, explore, exploration_config])	Sets the config's exploration settings.
fault_tolerance([recreate_failed_workers, ...])	Sets the config's fault tolerance settings.
framework([framework, eager_tracing, ...])	Sets the config's DL framework settings.
freeze()	Freezes this config object, such that no attributes can be set anymore.
from_dict(config_dict)	Creates an AlgorithmConfig from a legacy python config dict.
get(key[, default])	Shim method to help pretend we are a dict.
get_default_learner_class()	Returns the Learner class to use for this algorithm.
get_default_rl_module_spec()	Returns the RLModule spec to use for this algorithm.
get_evaluation_config_object()	Creates a full AlgorithmConfig object from self.evaluation_config.
get_learner_hyperparameters()	Returns a new LearnerHyperparameters instance for the respective Learner.
get_marl_module_spec(*, policy_dict[, ...])	Returns the MultiAgentRLModule spec based on the given policy spec dict.
get_multi_agent_setup(*[, policies, env, ...])	Compiles complete multi-agent config (dict) from the information in self.
get_rollout_fragment_length([worker_index])	Automatically infers a proper rollout_fragment_length setting if "auto".
get_torch_compile_learner_config()	Returns the TorchCompileConfig to use on learners.
get_torch_compile_worker_config()	Returns the TorchCompileConfig to use on workers.
is_multi_agent()	Returns whether this config specifies a multi-agent setup.
items()	Shim method to help pretend we are a dict.
keys()	Shim method to help pretend we are a dict.
multi_agent(*[, policies, ...])	Sets the config's multi-agent settings.
offline_data(*[, input_, input_config, ...])	Sets the config's offline data settings.
overrides(**kwargs)	Generates and validates a set of config key/value pairs (passed via kwargs).
pop(key[, default])	Shim method to help pretend we are a dict.
python_environment(*[, ...])	Sets the config's python environment settings.
reporting(*[, ...])	Sets the config's reporting settings.
resources(*[, num_gpus, _fake_gpus, ...])	Specifies resources allocated for an Algorithm and its ray actors/workers.
rl_module(*[, rl_module_spec, ...])	Sets the config's RLModule settings.
rollouts(*[, env_runner_cls, ...])	Sets the rollout worker configuration.
serialize()	Returns a mapping from str to JSON'able values representing this config.
to_dict()	Converts all settings into a legacy config dict for backward compatibility.
training(*[, gamma, lr, grad_clip, ...])	Sets the training related configuration.
update_from_dict(config_dict)	Modifies this AlgorithmConfig via the provided python config dict.
validate()	Validates all values in this config.
validate_train_batch_size_vs_rollout_fragment_length()	Detects mismatches for train_batch_size vs rollout_fragment_length.
values()	Shim method to help pretend we are a dict.

Attributes

is_atari	True if if specified env is an Atari env.
learner_class	Returns the Learner sub-class to use by this Algorithm.
multiagent
num_workers