ver Dec22ndv4

recorded action history

desktop_env/envs/desktop_env.py

@@ -91,10 +91,12 @@ class DesktopEnv(gym.Env):
         self.result_getter: Getter = getattr(getters, "get_{:}".format(self.evaluator["result"]["type"]))
         self.expected_getter: Getter = getattr(getters, "get_{:}".format(self.evaluator["expected"]["type"]))
 
-        # episodic stuffs, like tmp dir and counters
+        # episodic stuffs, like tmp dir and counters, will be updated or reset
+        # when calling self.reset()
         self.tmp_dir: str = self.tmp_dir_base # just an init value, updated during reset
         self._traj_no: int = -1
         self._step_no: int = 0
+        self.action_history: List[Dict[str, any]] = []
 
     def _start_emulator(self):
         while True:
@@ -166,6 +168,7 @@ class DesktopEnv(gym.Env):
         print("Setting counters...")
         self._traj_no += 1
         self._step_no = 0
+        self.action_history.clear()
 
         print("Setup new temp dir...")
         self.tmp_dir = tempfile.mkdtemp( prefix="{:d}.{:}.".format(self._traj_no, self.task_id)
@@ -200,6 +203,7 @@ class DesktopEnv(gym.Env):
         elif self.action_space == "pyautogui":
             # the set of all possible python commands insides `pyautogui`
             self.controller.execute_python_command(action)
+        self.action_history.append(action)
 
         # todo: maybe for the better here we need to add a logic to wait until the rendering is done
         time.sleep(pause)