Fix issues

Author: ArzhelaR

training/exploit_trimesh.py

@@ -29,7 +29,7 @@ def exploit():
     avg_steps, avg_wins, avg_rewards, final_meshes = testPolicy(actor, 30, dataset, 100)
 
     if avg_steps is not None:
-        plot_test_results(avg_rewards, avg_wins, avg_steps)
+        plot_test_results(avg_rewards, avg_wins, avg_steps, avg_wins)
     plot_dataset(final_meshes)