main.py

import os
import tensorflow as tf

from model import Model

# modifying code to work with newer tensor flow
tf.compat.v1.disable_v2_behavior()



flags = tf.compat.v1.app.flags
FLAGS = flags.FLAGS

flags.DEFINE_boolean('test', False, 'If true, test against a random strategy.')
flags.DEFINE_boolean('play', False, 'If true, play against a trained TD-Gammon strategy.')
flags.DEFINE_boolean('restore', False, 'If true, restore a checkpoint before training.')

model_path = os.environ.get('MODEL_PATH', 'models/')
summary_path = os.environ.get('SUMMARY_PATH', 'summaries/')
checkpoint_path = os.environ.get('CHECKPOINT_PATH', 'checkpoints/')

if not os.path.exists(model_path):
    os.makedirs(model_path)

if not os.path.exists(checkpoint_path):
    os.makedirs(checkpoint_path)

if not os.path.exists(summary_path):
    os.makedirs(summary_path)

if __name__ == '__main__':
    graph = tf.compat.v1.Graph()
    sess = tf.compat.v1.Session(graph=graph)
    with sess.as_default(), graph.as_default():
        model = Model(sess, model_path, summary_path, checkpoint_path, restore=FLAGS.restore)
        if FLAGS.test:
            model.test(episodes=1000)
        elif FLAGS.play:
            model.play()
        else:
            model.train()