Using Cleanup World

[devvramesh]

Hello. I'm looking to implement Cleanup World, but I don't see any examples. Could you point me in a direction for its use?

I tried implementing an example of CleanupWorld, and I got the following error: TypeError: (simple_rl): Reproduction of results not implemented for CleanUpMDP

Here is the code that I used:
`
#!/usr/bin/env python

#Python imports.
import sys

#Other imports.
import srl_example_setup
from simple_rl.agents import QLearningAgent, RandomAgent
from simple_rl.tasks import CleanUpMDP, CleanUpRoom, CleanUpTask, CleanUpDoor, CleanUpBlock
from simple_rl.run_experiments import run_agents_on_mdp

def main(open_plot=True):

task = CleanUpTask("green", "red")
room1 = CleanUpRoom("room1", [(x, y) for x in range(5) for y in range(3)], "blue")
block1 = CleanUpBlock("block1", 1, 1, color="green")
block2 = CleanUpBlock("block2", 2, 4, color="purple")
block3 = CleanUpBlock("block3", 8, 1, color="orange")
room2 = CleanUpRoom("room2", [(x, y) for x in range(5, 10) for y in range(3)], color="red")
room3 = CleanUpRoom("room3", [(x, y) for x in range(0, 10) for y in range(3, 6)], color="yellow")
rooms = [room1, room2, room3]
blocks = [block1, block2, block3]
doors = [CleanUpDoor(4, 0), CleanUpDoor(3, 2)]
mdp = CleanUpMDP(task, rooms=rooms, doors=doors, blocks=blocks)
# mdp.visualize_interaction()

# Make agents.
ql_agent = QLearningAgent(actions=mdp.get_actions())
rand_agent = RandomAgent(actions=mdp.get_actions())

# Run experiment and make plot.
run_agents_on_mdp([ql_agent, rand_agent], mdp, instances=10, episodes=50, steps=10, open_plot=open_plot)

if name == "main":
main(open_plot=not sys.argv[-1] == "no_plot")
`