eta_utility.eta_x.config module

class eta_utility.eta_x.config.ConfigOpt(*, config_name: str, path_root: Path, relpath_results: str, relpath_scenarios: str | None = None, setup: ConfigOptSetup, settings: ConfigOptSettings)

Bases: object

Configuration for the optimization, which can be loaded from a JSON file.

config_name: str

Name of the configuration used for the series of run.

path_root: pathlib.Path

Root path for the optimization run (scenarios and results are relative to this).

relpath_results: str

Relative path to the results folder.

relpath_scenarios: str | None

relative path to the scenarios folder (default: None).

path_results: pathlib.Path

Path to the results folder.

path_scenarios: pathlib.Path | None

Path to the scenarios folder (default: None).

setup: ConfigOptSetup

Optimization run setup.

settings: ConfigOptSettings

Optimization run settings.

classmethod from_json(file: Path, path_root: Path, overwrite: Mapping[str, Any] | None = None) → ConfigOpt

classmethod from_config_file(file: Path, path_root: Path, overwrite: Mapping[str, Any] | None = None) → ConfigOpt

Load configuration from JSON/TOML/YAML file, which consists of the following sections:

• paths: In this section, the (relative) file paths for results and scenarios are specified. The paths are deserialized directly into the ConfigOpt object.

• setup: This section specifies which classes and utilities should be used for optimization. The setup configuration is deserialized into the ConfigOptSetup object.

• settings: The settings section contains basic parameters for the optimization, it is deserialized into a ConfigOptSettings object.

• environment_specific: The environment section contains keyword arguments for the environment. This section must contain values for the arguments of the environment, the expected values are therefore different depending on the environment and not fully documented here.

• agent_specific: The agent section contains keyword arguments for the control algorithm (agent). This section must contain values for the arguments of the agent, the expected values are therefore different depending on the agent and not fully documented here.

Parameters:

• file – Path to the configuration file.

• overwrite – Config parameters to overwrite.

Returns:

ConfigOpt object.

classmethod from_dict(config: dict[str, Any], file: Path, path_root: pathlib.Path) → ConfigOpt

Build a ConfigOpt object from a dictionary of configuration options.

Parameters:

• config – Dictionary of configuration options.

• file – Path to the configuration file.

• path_root – Root path for the optimization configuration run.

Returns:

ConfigOpt object.

class eta_utility.eta_x.config.ConfigOptSetup(*, agent_import: str, environment_import: str, interaction_env_import: str | None = None, vectorizer_import='stable_baselines3.common.vec_env.dummy_vec_env.DummyVecEnv', policy_import='eta_utility.eta_x.common.NoPolicy', monitor_wrapper=False, norm_wrapper_obs=False, norm_wrapper_reward=False, tensorboard_log=False)

Bases: object

Configuration options as specified in the “setup” section of the configuration file.

agent_import: str

Import description string for the agent class.

agent_class: type[BaseAlgorithm]

Agent class (automatically determined from agent_import).

environment_import: str

Import description string for the environment class.

environment_class: type[BaseEnv]

Imported Environment class (automatically determined from environment_import).

interaction_env_import: str | None

Import description string for the interaction environment (default: None).

interaction_env_class: type[BaseEnv] | None

Interaction environment class (default: None) (automatically determined from interaction_env_import).

vectorizer_import: str

Import description string for the environment vectorizer (default: stable_baselines3.common.vec_env.dummy_vec_env.DummyVecEnv).

vectorizer_class: type[DummyVecEnv]

Environment vectorizer class (automatically determined from vectorizer_import).

policy_import: str

Import description string for the policy class (default: eta_utility.eta_x.agents.common.NoPolicy).

policy_class: type[BasePolicy]

Policy class (automatically determined from policy_import).

monitor_wrapper: bool

Flag which is true if the environment should be wrapped for monitoring (default: False).

norm_wrapper_obs: bool

Flag which is true if the observations should be normalized (default: False).

norm_wrapper_reward: bool

Flag which is true if the rewards should be normalized (default: False).

tensorboard_log: bool

Flag to enable tensorboard logging (default: False).

classmethod from_dict(dikt: dict[str, Any]) → ConfigOptSetup

class eta_utility.eta_x.config.ConfigOptSettings(*, seed=None, verbose=2, n_environments=1, n_episodes_play=None, n_episodes_learn=None, interact_with_env=False, save_model_every_x_episodes=10, plot_interval=10, episode_duration, sampling_time, sim_steps_per_sample=None, scale_actions=None, round_actions=None, environment=NOTHING, interaction_env: dict[str, Any] | None = None, agent=NOTHING, log_to_file=True)

Bases: object

seed: int | None

Seed for random sampling (default: None).

verbose: int

Logging verbosity of the framework (default: 2).

n_environments: int

Number of vectorized environments to instantiate (if not using DummyVecEnv) (default: 1).

n_episodes_play: int | None

Number of episodes to execute when the agent is playing (default: None).

n_episodes_learn: int | None

Number of episodes to execute when the agent is learning (default: None).

interact_with_env: bool

Flag to determine whether the interaction env is used or not (default: False).

save_model_every_x_episodes: int

How often to save the model during training (default: 10 - after every ten episodes).

plot_interval: int

How many episodes to pass between each render call (default: 10 - after every ten episodes).

episode_duration: float

Duration of an episode in seconds (can be a float value).

sampling_time: float

Duration between time samples in seconds (can be a float value).

sim_steps_per_sample: int | None

Simulation steps for every sample.

scale_actions: float | None

Multiplier for scaling the agent actions before passing them to the environment (especially useful with interaction environments) (default: None).

round_actions: int | None

Number of digits to round actions to before passing them to the environment (especially useful with interaction environments) (default: None).

environment: dict[str, Any]

Settings dictionary for the environment.

interaction_env: dict[str, Any] | None

Settings dictionary for the interaction environment (default: None).

agent: dict[str, Any]

Settings dictionary for the agent.

log_to_file: bool

Flag which is true if the log output should be written to a file

classmethod from_dict(dikt: dict[str, dict[str, Any]]) → ConfigOptSettings

class eta_utility.eta_x.config.ConfigOptRun(*, series: str, name: str, description, path_root: Path, path_results: Path, path_scenarios: Path | None = None)

Bases: object

Configuration for an optimization run, including the series and run names descriptions and paths for the run.

series: str

Name of the series of optimization runs.

name: str

Name of an optimization run.

description: str

Description of an optimization run.

path_root: pathlib.Path

Root path of the framework run.

path_results: pathlib.Path

Path to results of the optimization run.

path_scenarios: pathlib.Path | None

Path to scenarios used for the optimization run.

path_series_results: pathlib.Path

Path for the results of the series of optimization runs.

path_run_model: pathlib.Path

Path to the model of the optimization run.

path_run_info: pathlib.Path

Path to information about the optimization run.

path_run_monitor: pathlib.Path

Path to the monitoring information about the optimization run.

path_vec_normalize: pathlib.Path

Path to the normalization wrapper information.

path_net_arch: pathlib.Path

Path to the neural network architecture file.

path_log_output: pathlib.Path

Path to the log output file.

env_version: str | None

Version of the main environment.

env_description: str | None

Description of the main environment.

interaction_env_version: str | None

Version of the secondary environment (interaction_env).

interaction_env_description: str | None

Description of the secondary environment (interaction_env).

create_results_folders() → None

Create the results folders for an optimization run (or check if they already exist).

set_env_info(env: type[BaseEnv]) → None

Set the environment information of the optimization run to represent the given environment. The information will default to None if this is never called.

Parameters:

env – The environment whose description should be used.

set_interaction_env_info(env: type[BaseEnv]) → None

Set the interaction environment information of the optimization run to represent the given environment. The information will default to None if this is never called.

Parameters:

env – The environment whose description should be used.

property paths: dict[str, Path]

Dictionary of all paths for the optimization run. This is for easier access and contains all paths as mentioned above.