updated evaluation code for previous env changes

outdated code from previous changes on env

ml/run_eval.py

@@ -16,13 +16,14 @@ from ml.evaluate import evaluate
 
 
 def main():
-    parser = argparse.ArgumentParser()
+    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 'rounds' to run. One episode lasts from reset until the robot falls over or the time limit is reached.")
+    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("--num-robots", type=int, default=1, help="Number of robots in the evaluation 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")
+    parser.add_argument("--save-metrics", type=str, default=None, help="Optional path to save JSON metrics report")
     args = parser.parse_args()
 
     evaluate(
@@ -32,8 +33,9 @@ def main():
         num_robots=args.num_robots,
         robot_spacing=args.robot_spacing,
         start_pose=args.start_pose,
+        save_json=args.save_metrics,
     )
 
 
 if __name__ == "__main__":
-    main()
+    main()