mirror of
https://github.com/illiumst/marl-factory-grid.git
synced 2025-05-22 23:06:43 +02:00
93 lines
2.3 KiB
YAML
93 lines
2.3 KiB
YAML
General:
|
|
# RNG-seed to sample the same "random" numbers every time, to make the different runs comparable.
|
|
env_seed: 69
|
|
# Individual vs global rewards
|
|
individual_rewards: true
|
|
# The level.txt file to load from marl_factory_grid/levels
|
|
level_name: rooms
|
|
# Radius of Partially observable Markov decision process
|
|
pomdp_r: 3
|
|
# Print all messages and events
|
|
verbose: true
|
|
# Run tests
|
|
tests: false
|
|
|
|
# In the "clean and bring" Scenario one agent aims to pick up all items and drop them at drop-off locations while all
|
|
# other agents aim to clean dirt piles.
|
|
Agents:
|
|
# The clean agents
|
|
Wolfgang:
|
|
Actions:
|
|
- Move8
|
|
- DoorUse
|
|
- Clean
|
|
- Noop
|
|
Observations:
|
|
- Walls
|
|
- Doors
|
|
- Other
|
|
- DirtPiles
|
|
Clones: 8
|
|
|
|
# The item agent
|
|
Juergen:
|
|
Actions:
|
|
- Move8
|
|
- DoorUse
|
|
- ItemAction
|
|
- Noop
|
|
Observations:
|
|
- Walls
|
|
- Doors
|
|
- Other
|
|
- Items
|
|
- DropOffLocations
|
|
- Inventory
|
|
|
|
Entities:
|
|
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:
|
|
DropOffLocations:
|
|
coords_or_quantity: 1
|
|
max_dropoff_storage_size: 0
|
|
Inventories: { }
|
|
Items:
|
|
coords_or_quantity: 5
|
|
|
|
# Rules section specifies the rules governing the dynamics of the environment.
|
|
Rules:
|
|
# Environment Dynamics
|
|
# When stepping over a dirt pile, entities carry a ratio of the dirt to their next position
|
|
EntitiesSmearDirtOnMove:
|
|
smear_ratio: 0.2
|
|
# Doors automatically close after a certain number of time steps
|
|
DoorAutoClose:
|
|
close_frequency: 7
|
|
|
|
# Respawn Stuff
|
|
# Define how dirt should respawn after the initial spawn
|
|
RespawnDirt:
|
|
respawn_freq: 30
|
|
# Define how items should respawn after the initial spawn
|
|
RespawnItems:
|
|
respawn_freq: 50
|
|
|
|
# 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 all dirt is cleaned
|
|
DoneOnAllDirtCleaned:
|
|
DoneAtMaxStepsReached:
|
|
max_steps: 500
|