updated readme

README.md

@@ -3,7 +3,7 @@
 Tackling emergent dysfunctions (EDYs) in cooperation with Fraunhofer-IKS
 
 ## Setup
-Just install this environment by `pip install marl-factory-grid`.
+Install this environment using `pip install marl-factory-grid`.
 
 ## First Steps
 
@@ -13,59 +13,157 @@ Most of the env. objects (entites, rules and assets) can be loaded automatically
 Just define what your environment needs in a *yaml*-configfile like:
 
 <details><summary>Example ConfigFile</summary>    
+    
+    # Default Configuration File
+    
     General:
-    level_name: rooms
+      # RNG-seed to sample the same "random" numbers every time, to make the different runs comparable.
-    env_seed: 69
+      env_seed: 69
-    verbose: !!bool False
+      # Individual vs global rewards
-    pomdp_r: 5
+      individual_rewards: true
-    individual_rewards: !!bool True
+      # The level.txt file to load from marl_factory_grid/levels
-
+      level_name: large
-    Entities:
+      # View Radius; 0 = full observatbility
-        Defaults: {}
+      pomdp_r: 3
-        Doors:
+      # Print all messages and events
-            closed_on_init: True
+      verbose: false
-            auto_close_interval: 10
+      # Run tests
-            indicate_area: False
+      tests: false
-        Destinations: {}
+    
-
+    # Agents section defines the characteristics of different agents in the environment.
+    
+    # An Agent requires a list of actions and observations.
+    # Possible actions: Noop, Charge, Clean, DestAction, DoorUse, ItemAction, MachineAction, Move8, Move4, North, NorthEast, ...
+    # Possible observations: All, Combined, GlobalPosition, Battery, ChargePods, DirtPiles, Destinations, Doors, Items, Inventory, DropOffLocations, Maintainers, ...
+    # You can use 'clone' as the agent name to have multiple instances with either a list of names or an int specifying the number of clones.
     Agents:
-        Wolfgang:
+      Wolfgang:
-            Actions:
+        Actions:
-                - Move8
+          - Noop
-                - Noop
+          - Charge
-                - DoorUse
+          - Clean
-                - ItemAction
+          - DestAction
-            Observations:
+          - DoorUse
-                - All
+          - ItemAction
-                - Placeholder
+          - Move8
-                - Walls
+        Observations:
-                - Items
+          - Combined:
-                - Placeholder
+              - Other
-                - Doors
+              - Walls
-                - Doors
+          - GlobalPosition
-        Armin:
+          - Battery
-            Actions:
+          - ChargePods
-                - Move4
+          - DirtPiles
-                - ItemAction
+          - Destinations
-                - DoorUse
+          - Doors
-            Observations:
+          - Items
-                - Combined:
+          - Inventory
-                    - Agent['Wolfgang']
+          - DropOffLocations
-                    - Walls
+          - Maintainers
-                    - Doors
+    
-                    - Items
+    # Entities section defines the initial parameters and behaviors of different entities in the environment.
+    # Entities all spawn using coords_or_quantity, a number of entities or coordinates to place them.
+    Entities:
+      # Batteries: Entities representing power sources for agents.
+      Batteries:
+        initial_charge: 0.8
+        per_action_costs: 0.02
+    
+      # ChargePods: Entities representing charging stations for Batteries.
+      ChargePods:
+        coords_or_quantity: 2
+    
+      # Destinations: Entities representing target locations for agents.
+      # - spawn_mode: GROUPED or SINGLE. Determines how destinations are spawned.
+      Destinations:
+        coords_or_quantity: 1
+        spawn_mode: GROUPED
+    
+      # DirtPiles: Entities representing piles of dirt.
+      # - initial_amount: Initial amount of dirt in each pile.
+      # - clean_amount: Amount of dirt cleaned in each cleaning action.
+      # - dirt_spawn_r_var: Random variation in dirt spawn amounts.
+      # - max_global_amount: Maximum total amount of dirt allowed in the environment.
+      # - max_local_amount: Maximum amount of dirt allowed in one position.
+      DirtPiles:
+        coords_or_quantity: 10
+        initial_amount: 2
+        clean_amount: 1
+        dirt_spawn_r_var: 0.1
+        max_global_amount: 20
+        max_local_amount: 5
+    
+      # Doors are spawned using the level map.
+      Doors:
+    
+      # DropOffLocations: Entities representing locations where agents can drop off items.
+      # - max_dropoff_storage_size: Maximum storage capacity at each drop-off location.
+      DropOffLocations:
+        coords_or_quantity: 1
+        max_dropoff_storage_size: 0
+    
+      # GlobalPositions.
+      GlobalPositions: { }
+    
+      # Inventories: Entities representing inventories for agents.
+      Inventories: { }
+    
+      # Items: Entities representing items in the environment.
+      Items:
+        coords_or_quantity: 5
+    
+      # Machines: Entities representing machines in the environment.
+      Machines:
+        coords_or_quantity: 2
+    
+      # Maintainers: Entities representing maintainers that aim to maintain machines.
+      Maintainers:
+        coords_or_quantity: 1
+    
+      # Zones: Entities representing zones in the environment.
+      Zones: { }
+    
+    
+    # Rules section specifies the rules governing the dynamics of the environment.
     Rules:
-        Defaults: {}
+      # Environment Dynamics
-        WatchCollisions:
+      # When stepping over a dirt pile, entities carry a ratio of the dirt to their next position
-            done_at_collisions: !!bool True
+      EntitiesSmearDirtOnMove:
-        ItemRespawn:
+        smear_ratio: 0.2
-            spawn_freq: 5
+      # Doors automatically close after a certain number of time steps
-        DoorAutoClose: {}
+      DoorAutoClose:
+        close_frequency: 10
+      # Maintainers move at every time step
+      MoveMaintainers:
+    
+      # Respawn Stuff
+      # Define how dirt should respawn after the initial spawn
+      RespawnDirt:
+        respawn_freq: 15
+      # Define how items should respawn after the initial spawn
+      RespawnItems:
+        respawn_freq: 15
+    
+      # Utilities
+      # 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
+    
+      # Done Conditions
+      # Define the conditions for the environment to stop. Either success or a fail conditions.
+      # The environment stops when an agent reaches a destination
+      DoneAtDestinationReach:
+      # The environment stops when all dirt is cleaned
+      DoneOnAllDirtCleaned:
+      # The environment stops when a battery is discharged
+      DoneAtBatteryDischarge:
+      # The environment stops when a maintainer reports a collision
+      DoneAtMaintainerCollision:
+      # The environment stops after max steps
+      DoneAtMaxStepsReached:
+        max_steps: 500
 
-    Assets:
-    - Defaults
-    - Items
-    - Doors
    </details>
 
 Have a look in [\quickstart](./quickstart) for further configuration examples.
@@ -80,12 +178,11 @@ General:
     level_name: rooms  # 'double', 'large', 'simple', ...
 ```
 ... or create your own , maybe with the help of [asciiflow.com](https://asciiflow.com/#/).
-Make sure to use `#` as [Walls](marl_factory_grid/environment/entity/wall.py), `-` as free (walkable) [Floor](marl_factory_grid/environment/entity/wall.py)-Tiles, `D` for [Walls](./modules/doors/entities.py).
+Make sure to use `#` as [Walls](marl_factory_grid/environment/entity/wall.py), `-` as free (walkable) floor, `D` for [Walls](./modules/doors/entities.py).
 Other Entites (define you own) may bring their own `Symbols`
 
 #### Entites
-Entites, either [Objects](marl_factory_grid/environment/entity/object.py) for tracking stats 
+Entites are [Objects](marl_factory_grid/environment/entity/object.py) that can additionally be assigned a position.
-or env. [Entity](marl_factory_grid/environment/entity/entity.py) which can interact.
 Abstract Entities are provided.
 
 #### Groups

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