agents.py

#!/usr/bin/env python

import algo
import random
import time

tetris = algo.TetrisLearningProblem()

while not tetris.is_terminal():
    actions = tetris.get_possible_actions()
    a = random.choice(actions)
    reward = tetris.perform_action(a)
    algo.print_grid(tetris.board)

    print "Reward: ", reward
    time.sleep(0.5)