scores = []
choices = []
for each_game in range(100):
    score = 0
    prev_obs = []
    for step_index in range(goal_steps):
         env.render()
        if len(prev_obs)==0:
            action = random.randrange(0,2)
        else:
            action = np.argmax(trained_model.predict(prev_obs.reshape(-1, len(prev_obs)))[0])

        choices.append(action)
        new_observation, reward, done, info = env.step(action)
        prev_obs = new_observation
        score+=reward
        if done:
            break

    env.reset()
    scores.append(score)

print(scores)
print('Average Score:', sum(scores)/len(scores))
print('choice 1:{}  choice 0:{}'.format(choices.count(1)/len(choices),choices.count(0)/len(choices)))