JackM323
acb3d671be
new reward/penalty system learning phases with curriculum learning new training parameters cleanup of old code better logging while training multiple environments instead of robots (they could bumb into each other)
41 lines
1.6 KiB
Python
41 lines
1.6 KiB
Python
"""Run a trained policy in the PyBullet sim for quick inspection.
|
|
|
|
Usage:
|
|
python ml/run_eval.py --model ml/checkpoints/ppo_joint_command.zip --episodes 3 --gui
|
|
"""
|
|
|
|
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.evaluate import evaluate
|
|
|
|
|
|
def main():
|
|
parser = argparse.ArgumentParser(description="JackBot Policy Evaluator Wrapper")
|
|
parser.add_argument("--model", type=str, required=True, help="Path to the trained model file (.zip)")
|
|
parser.add_argument("--episodes", type=int, default=3, help="Number of evaluation episodes to run.")
|
|
parser.add_argument("--gui", action="store_true", help="Show the PyBullet GUI during evaluation")
|
|
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")
|
|
parser.add_argument("--random-command", action="store_true", help="Randomize command samples during evaluation")
|
|
parser.add_argument("--save-metrics", type=str, default=None, help="Optional path to save JSON metrics report")
|
|
args = parser.parse_args()
|
|
|
|
evaluate(
|
|
model_path=args.model,
|
|
episodes=args.episodes,
|
|
use_gui=args.gui,
|
|
robot_spacing=args.robot_spacing,
|
|
start_pose=args.start_pose,
|
|
random_command=args.random_command,
|
|
save_json=args.save_metrics,
|
|
)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main() |