embodichain.agents.rl.train

Overview

Training entry points and command-line helpers for launching RL experiments.

Functions

cli()	Command-line interface for RL training.
parse_args()	Parse command line arguments.
train_from_config(config_path[, distributed])	Run training from a config file path.

Functions:

cli()	Command-line interface for RL training.
parse_args()	Parse command line arguments.
train_from_config(config_path[, distributed])	Run training from a config file path.

embodichain.agents.rl.train.cli()

Command-line interface for RL training.

Parses CLI arguments and launches training from a config file.

Return type:

None

embodichain.agents.rl.train.parse_args()

Parse command line arguments.

embodichain.agents.rl.train.train_from_config(config_path, distributed=None)

Run training from a config file path.

Parameters:

• config_path (str) – Path to the training config file (.json, .yaml, or .yml).

• distributed (Optional[bool]) – If True, run multi-GPU distributed training. If None, use trainer.distributed from config.