twisterl package

Submodules

• twisterl.rl package
• twisterl.envs package
• twisterl.nn package

twisterl.train module

The main training entry point. Run training via:

python -m twisterl.train --config <path_to_config.json>

twisterl.utils module

Utility functions for loading configs and preparing algorithms.

Key functions:

• prepare_algorithm(config, run_path, load_checkpoint_path): Prepares an algorithm instance from config

• load_config(config_path): Loads a JSON config file

• load_checkpoint(checkpoint_path): Loads a checkpoint from either safetensors or pt format

• pull_hub_algorithm(repo_id, model_path, revision, validate): Downloads models from HuggingFace Hub

twisterl.defaults module

Default configuration values for algorithms, training, and evaluation.

twisterl.defaults.make_config(algo_name, input_config)