Evaluation Phase Usage

ml/run_eval.py

@@ -1,7 +1,7 @@
-"""Run a trained policy in the PyBullet sim for quick inspection.
+"""Run a trained policy in the PyBullet sim with full curriculum progression.
 
 Usage:
-    python ml/run_eval.py --model ml/checkpoints/ppo_joint_command.zip --episodes 3 --gui
+    python ml/run_eval.py --model ml/checkpoints/ppo_joint_command.zip --episodes 5 --gui
 """
 
 import argparse
@@ -16,13 +16,14 @@ from ml.evaluate import evaluate
 
 
 def main():
-    parser = argparse.ArgumentParser(description="JackBot Policy Evaluator Wrapper")
+    parser = argparse.ArgumentParser(description="JackBot Curriculum 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("--episodes", type=int, default=5, 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("--no-random-command", dest="random_command", action="store_false", help="Disable command sampling and lock to zero commands")
+    parser.set_defaults(random_command=True)
     parser.add_argument("--save-metrics", type=str, default=None, help="Optional path to save JSON metrics report")
     args = parser.parse_args()