t-dlmodel.py

import gym
import random
import numpy as np
from keras.models     import Sequential
from keras.layers     import Dense
from keras.optimizers import Adam

# Let's create the Cart Pole OpenAI Gym game environment and define some constants
env = gym.make('CartPole-v1')
env.reset()
goal_steps = 500
score_requirement = 60
intial_games = 10000

def model_data_preparation():
    training_data = []
    accepted_scores = []
    for game_index in range(intial_games):
        score = 0
        game_memory = []
        previous_observation = []
        for step_index in range(goal_steps):
            action = random.randrange(0, 2)
            observation, reward, done, info = env.step(action)
            
            if len(previous_observation) > 0:
                game_memory.append([previous_observation, action])
                
            previous_observation = observation
            score += reward
            if done:
                break
            
        if score >= score_requirement:
            accepted_scores.append(score)
            for data in game_memory:
                if data[1] == 1:
                    output = [0, 1]
                elif data[1] == 0:
                    output = [1, 0]
                training_data.append([data[0], output])
        
        env.reset()

    print(accepted_scores)
    
    return training_data

training_data = model_data_preparation()



# Please create a binary classifier neural network and train it with *training_data*
trained_model = #YOUR_CODE_HERE


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)))