config rl

overcooked_simulator/game_content/environment_config_rl.yaml

+plates:
+  clean_plates: 1
+  dirty_plates: 2
+  plate_delay: [ 5, 10 ]
+  # range of seconds until the dirty plate arrives.
+
+game:
+  time_limit_seconds: 300
+
+meals:
+  all: true
+  # if all: false -> only orders for these meals are generated
+  # TODO: what if this list is empty?
+  list:
+    - TomatoSoup
+    - OnionSoup
+    - Salad
+
+layout_chars:
+  _: Free
+  hash: Counter
+  A: Agent
+  pipe: Extinguisher
+  P: PlateDispenser
+  C: CuttingBoard
+  X: Trashcan
+  W: ServingWindow
+  S: Sink
+  +: SinkAddon
+  U: Pot  # with Stove
+  Q: Pan  # with Stove
+  O: Peel  # with Oven
+  F: Basket  # with DeepFryer
+  T: Tomato
+  N: Onion  # oNioN
+  L: Lettuce
+  K: Potato  # Kartoffel
+  I: Fish  # fIIIsh
+  D: Dough
+  E: Cheese  # chEEEse
+  G: Sausage  # sausaGe
+  B: Bun
+  M: Meat
+
+
+orders:
+  order_gen_class: !!python/name:overcooked_simulator.order.RandomOrderGeneration ''
+  # the class to that receives the kwargs. Should be a child class of OrderGeneration in order.py
+  order_gen_kwargs:
+    order_duration_random_func:
+      # how long should the orders be alive
+      # 'random' library call with getattr, kwargs are passed to the function
+      func: uniform
+      kwargs:
+        a: 40
+        b: 60
+    max_orders: 6
+    # maximum number of active orders at the same time
+    num_start_meals: 2
+    # number of orders generated at the start of the environment
+    sample_on_dur_random_func:
+      # 'random' library call with getattr, kwargs are passed to the function
+      func: uniform
+      kwargs:
+        a: 10
+        b: 20
+    sample_on_serving: false
+    # Sample the delay for the next order only after a meal was served.
+    score_calc_gen_func: !!python/name:overcooked_simulator.order.simple_score_calc_gen_func ''
+    score_calc_gen_kwargs:
+      # the kwargs for the score_calc_gen_func
+      other: 0
+      scores: []
+    expired_penalty_func: !!python/name:overcooked_simulator.order.simple_expired_penalty ''
+    expired_penalty_kwargs:
+      default: 0
+  serving_not_ordered_meals: !!python/name:overcooked_simulator.order.serving_not_ordered_meals_with_five_score ''
+  # a func that calcs a store for not ordered but served meals. Input: meal
+  penalty_for_trash: !!python/name:overcooked_simulator.order.penalty_for_each_item ''
+  # a func that calcs the penalty for items that the player puts into the trashcan.
+
+player_config:
+  radius: 0.4
+  player_speed_units_per_seconds: 1
+  interaction_range: 1.6
+  restricted_view: False
+  view_angle: 95
+
+effect_manager:
+  FireManager:
+    class: !!python/name:overcooked_simulator.effect_manager.FireEffectManager ''
+    kwargs:
+      spreading_duration: [ 5, 10 ]
+      fire_burns_ingredients_and_meals: true
+
+
+extra_setup_functions:
+  #  json_states:
+  #    func: !!python/name:overcooked_simulator.recording.class_recording_with_hooks ''
+  #    kwargs:
+  #      hooks: [ json_state ]
+  #      log_class: !!python/name:overcooked_simulator.recording.LogRecorder ''
+  #      log_class_kwargs:
+  #        log_path: USER_LOG_DIR/ENV_NAME/json_states.jsonl
+  actions:
+    func: !!python/name:overcooked_simulator.recording.class_recording_with_hooks ''
+    kwargs:
+      hooks: [ pre_perform_action ]
+      log_class: !!python/name:overcooked_simulator.recording.LogRecorder ''
+      log_class_kwargs:
+        log_path: USER_LOG_DIR/ENV_NAME/LOG_RECORD_NAME.jsonl
+  random_env_events:
+    func: !!python/name:overcooked_simulator.recording.class_recording_with_hooks ''
+    kwargs:
+      hooks: [ order_duration_sample, plate_out_of_kitchen_time ]
+      log_class: !!python/name:overcooked_simulator.recording.LogRecorder ''
+      log_class_kwargs:
+        log_path: USER_LOG_DIR/ENV_NAME/LOG_RECORD_NAME.jsonl
+        add_hook_ref: true
+  env_configs:
+    func: !!python/name:overcooked_simulator.recording.class_recording_with_hooks ''
+    kwargs:
+      hooks: [ env_initialized, item_info_config ]
+      log_class: !!python/name:overcooked_simulator.recording.LogRecorder ''
+      log_class_kwargs:
+        log_path: USER_LOG_DIR/ENV_NAME/LOG_RECORD_NAME.jsonl
+        add_hook_ref: true
+

overcooked_simulator/gym_env.py

@@ -122,7 +122,7 @@ class EnvGymWrapper(Env):
 
         self.gridsize = 20
         environment_config_path: Path = (
-            ROOT_DIR / "game_content" / "environment_config.yaml"
+            ROOT_DIR / "game_content" / "environment_config_rl.yaml"
         )
         layout_path: Path = ROOT_DIR / "game_content" / "layouts" / "rl.layout"
         item_info_path: Path = ROOT_DIR / "game_content" / "item_info.yaml"
@@ -149,7 +149,7 @@ class EnvGymWrapper(Env):
             self.action_space_map[idx] = item
 
 
-        self.global_step_time = 0.5
+        self.global_step_time = 1
         self.in_between_steps = 1
 
         self.action_space = spaces.Discrete(len(self.action_space_map))
@@ -195,7 +195,7 @@ class EnvGymWrapper(Env):
     def reset(self, seed=None, options=None):
 
         environment_config_path: Path = (
-                ROOT_DIR / "game_content" / "environment_config.yaml"
+                ROOT_DIR / "game_content" / "environment_config_rl.yaml"
         )
         layout_path: Path = ROOT_DIR / "game_content" / "layouts" / "rl.layout"
         item_info_path: Path = ROOT_DIR / "game_content" / "item_info.yaml"