started visualization of routes in plot single runs, assets missing.

marl_factory_grid/algorithms/static/TSP_base_agent.py

@@ -33,10 +33,12 @@ class TSPBaseAgent(ABC):
         self.local_optimization = True
         self._env = state
         self.state = self._env.state[c.AGENT][agent_i]
+        self.spawn_position = np.array(self.state.pos)
         self._position_graph = self.generate_pos_graph()
         self._static_route = None
         self.cached_route = None
         self.fallback_action = None
+        self.action_list = []
 
     @abstractmethod
     def predict(self, *_, **__) -> int:

marl_factory_grid/algorithms/static/TSP_dirt_agent.py

@@ -30,6 +30,7 @@ class TSPDirtAgent(TSPBaseAgent):
             action = self._use_door_or_move(door, di.DIRT)
         else:
             action = self._predict_move(di.DIRT)
+        self.action_list.append(action)
         # Translate the action_object to an integer to have the same output as any other model
         try:
             action_obj = next(action_i for action_i, a in enumerate(self.state.actions) if a.name == action)

marl_factory_grid/algorithms/static/TSP_item_agent.py

@@ -38,6 +38,7 @@ class TSPItemAgent(TSPBaseAgent):
             action = self._use_door_or_move(door, i.DROP_OFF if self.mode == MODE_BRING else i.ITEM)
         else:
             action = self._choose()
+        self.action_list.append(action)
         # Translate the action_object to an integer to have the same output as any other model
         try:
             action_obj = next(action_i for action_i, a in enumerate(self.state.actions) if a.name == action)

marl_factory_grid/algorithms/static/TSP_target_agent.py

@@ -38,6 +38,7 @@ class TSPTargetAgent(TSPBaseAgent):
             action = self._use_door_or_move(door, d.DESTINATION)
         else:
             action = self._predict_move(d.DESTINATION)
+        self.action_list.append(action)
         # Translate the action_object to an integer to have the same output as any other model
         try:
             action_obj = next(action_i for action_i, a in enumerate(self.state.actions) if a.name == action)