feat: add headless option and play buttion function

exts/StrideSim/StrideSim/base_sample/base_sample_extension.py

@@ -8,6 +8,7 @@
 #
 
 import asyncio
+import subprocess
 import weakref
 from abc import abstractmethod
 
@@ -280,11 +281,9 @@ def _on_train(self):
         training_window = self._headless_dropdown.model.get_item_value_model().get_value_as_string()
 
         command = f"python {RL_DIR}/train.py --task {task_name}"
-        if training_window == "off":
+        if training_window == "1":
             command += " --headless"
 
-        import subprocess
-
         try:
             subprocess.Popen(command, shell=True)
             print(f"Started training process: {command}")
@@ -293,5 +292,16 @@ def _on_train(self):
         return
 
     def _on_play(self):
-        print("Playing")
+        task_name = self._rl_task_name_field.model.get_value_as_string()
+        training_window = self._headless_dropdown.model.get_item_value_model().get_value_as_string()
+
+        command = f"python {RL_DIR}/play.py --task {task_name}"
+
+        command += " --num_envs 10"
+
+        try:
+            subprocess.Popen(command, shell=True)
+            print(f"Started training process: {command}")
+        except Exception as e:
+            print(f"Error starting training process: {e}")
         return

rl/train.py

@@ -21,6 +21,7 @@
 parser.add_argument("--task", type=str, default=None, help="Name of the task.")
 parser.add_argument("--seed", type=int, default=None, help="Seed used for the environment")
 parser.add_argument("--max_iterations", type=int, default=None, help="RL Policy training iterations.")
+
 # append RSL-RL cli arguments
 cli_args.add_rsl_rl_args(parser)
 # append AppLauncher cli args