updated readme

marl_factory_grid/configs/clean_and_bring.yaml

@@ -8,7 +8,7 @@ General:
   # Radius of Partially observable Markov decision process
   pomdp_r: 3
   # Print all messages and events
-  verbose: True
+  verbose: true
   # Run tests
   tests: false
 
@@ -79,7 +79,8 @@ Rules:
     respawn_freq: 50
 
   # Utilities
-  # Define what happens on entity collisions
+  # This rule defines the collision mechanic, introduces a related DoneCondition and lets you specify rewards.
+  # Can be omitted/ignored if you do not want to take care of collisions at all.
   WatchCollisions:
     done_at_collisions: false
 

marl_factory_grid/configs/default_config.yaml

@@ -129,7 +129,8 @@ Rules:
     respawn_freq: 15
 
   # Utilities
-  # Define what happens on entity collisions
+  # This rule defines the collision mechanic, introduces a related DoneCondition and lets you specify rewards.
+  # Can be omitted/ignored if you do not want to take care of collisions at all.
   WatchCollisions:
     done_at_collisions: false
 

marl_factory_grid/configs/eight_puzzle.yaml

@@ -84,6 +84,6 @@ Rules:
     # On every step, should there be a reward for agets that reach their associated destination? No!
     dest_reach_reward: 0  # Do not touch. This is usefull in other settings!
     # Reward should only be given when all destiantions are reached in parallel!
-    condition: "simultanious"
+    condition: "simultaneous"
     # Reward if this is the case. Granted to each agent when all agents are at their target position simultaniously.
     reward_at_done: 1

marl_factory_grid/configs/two_rooms_one_door.yaml

@@ -50,7 +50,7 @@ Rules:
     close_frequency: 10
 
   # Utilities
-  # Define what happens on entity collisions
+  # This rule defines the collision mechanic, introduces a related DoneCondition and lets you specify rewards.
   WatchCollisions:
     done_at_collisions: false