Flattened Int converter and supressed logs

cooperative_cuisine/counters.py

@@ -717,7 +717,7 @@ class PlateDispenser(Counter):
                 [self.create_item() for _ in range(self.plate_config.dirty_plates)]
             )
         if self.plate_config.clean_plates > 0:
-            log.info(f"Setup {self.plate_config.dirty_plates} clean plates.")
+            #log.info(f"Setup {self.plate_config.dirty_plates} clean plates.")
             self.occupied_by.extend(
                 [
                     self.create_item(clean=True)

cooperative_cuisine/environment.py

@@ -587,7 +587,7 @@ class Environment:
             for callback_name, setup_kwargs in self.environment_config[
                 "hook_callbacks"
             ].items():
-                log.info(f"Setup hook callback {callback_name}")
+                #log.info(f"Setup hook callback {callback_name}")
                 hooks_via_callback_class(name=callback_name, env=self, **setup_kwargs)
 
     def increment_score(self, score: int | float, info: str = ""):

cooperative_cuisine/hooks.py

@@ -615,7 +615,7 @@ class Hooks:
 
 def print_hook_callback(text, env, **kwargs):
     """Dummy hook callback. Print env time and hook ref."""
-    print(env.env_time, text)
+    #print(env.env_time, text)
 
 
 class HookCallbackClass:

cooperative_cuisine/reinforcement_learning/obs_converter/advanced_converter_int.py

@@ -109,8 +109,7 @@ class AdvancedStateConverterInt(StateToObservationConverter):
         for free_idx in grid_idxs:
             grid[free_idx[0]][free_idx[1]].append(self.counter_list.index("Empty"))
             grid[free_idx[0]][free_idx[1]].append(self.counter_list.index("Empty"))
-        print(grid)
-        return np.array(grid)
+        return np.array(grid).flatten()
 
     def vectorize_item(self, item, item_list):
         if item is None:

cooperative_cuisine/reinforcement_learning/play_gym.py

 import hydra
+import stable_baselines3.common.env_checker
 from gymnasium.utils.play import play
 from omegaconf import DictConfig
 
@@ -11,6 +12,7 @@ def main(cfg: DictConfig):
     Enables steering the agent in the environment used for rl.
     """
     env = EnvGymWrapper(cfg)
+    stable_baselines3.common.env_checker.check_env(env)
     env.render_mode = "rgb_array"
     play(env, keys_to_action={"a": 2, "d": 3, "w": 0, "s": 1, " ": 4, "k": 5}, noop=8)