Petting Zoo tutorial

petting_zoo_tutorial.py

"""PettingZoo

Tutorial from: https://nbviewer.org/github/gsverhoeven/gt_rl_course/blob/master/week_8/marl_tictactoe.ipynb

Setup:

    pipenv install pettingzoo[classic]
"""

import random
import numpy as np
from collections import defaultdict

from pettingzoo.classic import tictactoe_v3


def policy(observation, agent):
    action = random.choice(np.flatnonzero(observation['action_mask']))
    return action


env = tictactoe_v3.env()

env.reset()
for i, agent in enumerate(env.agent_iter()):
    observation, reward, done, info = env.last()
    action = policy(observation, agent) if not done else None
    env.step(action)
    print("Round {}...".format(i))
    env.render()  # this visualizes a single game

# TODO: about q learning from the tutorial