NMZivkovic

def act(self, frame):
    if np.random.rand() <= self.epsilon:
        return self.enviroment.action_space.sample()

    frame = np.expand_dims(np.asarray(frame).astype(np.float64), axis=0)

    q_values = self.q_network.predict(frame)
    return np.argmax(q_values[0])

NMZivkovic

def _build_compile_model(self):
        model = Sequential()
        model.add(Conv2D(32, 8, strides=(4, 4), padding="valid",activation="relu", 
                              input_shape = self._image_shape))
        model.add(Conv2D(64, 4, strides=(2, 2), padding="valid", activation="relu",
                              input_shape = self._image_shape))
        model.add(Conv2D(64, 3, strides=(1, 1), padding="valid",activation="relu",
                              input_shape = self._image_shape))
        model.add(Flatten())
        model.add(Dense(512, activation="relu"))

NMZivkovic

def __init__(self, enviroment, optimizer, image_shape):
        
        # Initialize atributes
        self._action_size = enviroment.action_space.n
        self._optimizer = optimizer
        self._image_shape = image_shape
        self.enviroment = enviroment
        
        self.expirience_replay = deque(maxlen=100000)
        

NMZivkovic

class Agent(object):
    def __init__(self, enviroment, optimizer, image_shape):
        
        # Initialize atributes
        self._action_size = enviroment.action_space.n
        self._optimizer = optimizer
        self._image_shape = image_shape
        self.enviroment = enviroment
        
        self.expirience_replay = deque(maxlen=100000)

NMZivkovic

enviroment.reset()

frames = []
for _ in range(NUMBER_OF_FRAMES):
    enviroment.step(enviroment.action_space.sample())
    frames.append(enviroment.ale.getScreenRGB())
img_processor.plot_frames(frames)

NMZivkovic

GAME_NAME = "BreakoutDeterministic-v4"
NUMBER_OF_FRAMES = 5

enviroment = gym.make(GAME_NAME).env

NMZivkovic

import numpy as np
import random
from collections import deque

import matplotlib.pyplot as plt
from PIL import Image
import imageio

import os
import gym

NMZivkovic

// Set the training algorithm 
var trainer = mlContext.Regression.Trainers.FastTree(
                              new FastTreeRegressionTrainer.Options() { 
                                            NumberOfLeaves = 98, 
                                            MinimumExampleCountPerLeaf = 10, 
                                            NumberOfTrees = 500, 
                                            LearningRate = 0.07655732f, 
                                            Shrinkage = 0.2687001f, 
                                            LabelColumnName = "season", 
                                            FeatureColumnName = "Features" 

NMZivkovic

static void Main(string[] args)
{

    var regressors = new List<IEstimator<ITransformer>>()
    {
        _mlContext.Regression.Trainers.Sdca(labelColumnName: "Count", featureColumnName: "Features"),
        _mlContext.Regression.Trainers.LbfgsPoissonRegression(labelColumnName: "Count", featureColumnName: "Features"),
        _mlContext.Regression.Trainers.FastForest(labelColumnName: "Count", featureColumnName: "Features"),
        _mlContext.Regression.Trainers.FastTree(labelColumnName: "Count", featureColumnName: "Features"),
        _mlContext.Regression.Trainers.FastTreeTweedie(labelColumnName: "Count", featureColumnName: "Features"),

NMZivkovic

using BikeSharingDemand.Helpers;
using BikeSharingDemand.ModelNamespace;
using Microsoft.ML;
using System;
using System.Collections.Generic;
using System.Linq;

namespace BikeSharingDemand
{
    class Program