"""Minimal training launcher for quick experiments.

Usage:
    python ml/run_train.py --timesteps 50000 --model ml/checkpoints/ppo_joint_command

This is a convenience wrapper around `ml.train.train` with friendly defaults
for interactive experimentation.
"""

import argparse
import sys
from pathlib import Path

ROOT_DIR = Path(__file__).resolve().parent.parent
if str(ROOT_DIR) not in sys.path:
    sys.path.insert(0, str(ROOT_DIR))

from ml.train import train


def main():
    parser = argparse.ArgumentParser()
    parser.add_argument("--timesteps", type=int, default=50000, help="Total number of 'practice steps'.")
    parser.add_argument("--model", type=str, default="ml/checkpoints/ppo_joint_command", help="Path to save the trained model")
    parser.add_argument("--seed", type=int, default=0, help="Random seed for reproducibility")
    parser.add_argument("--device", type=str, default="auto", help="Device to use: 'cpu', 'cuda', or 'auto'")
    parser.add_argument("--gui", action="store_true", help="Show the PyBullet GUI during training")
    parser.add_argument("--num-robots", type=int, default=1, help="Number of robots in the training environment")
    parser.add_argument("--robot-spacing", type=float, default=0.5, help="Spacing between robots in meters")
    parser.add_argument("--start-pose", type=str, choices=["init_deg", "init90_deg"], default="init_deg", help="Initial robot pose at reset")
    args = parser.parse_args()

    Path(args.model).parent.mkdir(parents=True, exist_ok=True)
    train(
        total_timesteps=args.timesteps,
        model_path=args.model,
        seed=args.seed,
        device=args.device,
        use_gui=args.gui,
        num_robots=args.num_robots,
        robot_spacing=args.robot_spacing,
        start_pose=args.start_pose,
    )


if __name__ == "__main__":
    main()