araffin

def preprocessImage(image, width, height):
    """
    Preprocessing script to convert image into neural net input array
    :param image: (cv2 RBG image)
    :param width: (int)
    :param height: (int)
    :return: (numpy array)
    """
    image = cv2.resize(image, (width, height), interpolation=cv2.INTER_LINEAR)
    x = image.flatten()  # create a big 1D-array

araffin

// Extracted from https://github.com/araffin/cpp-arduino-serial/
#include <robust_serial.hpp>

// Open Serial Port
serial_file.open(serial_filename);

// Send the order "MOTOR", i.e. to change the speed of the car
write_order(serial_file, MOTOR);
// with parameter speed=56 (going forward at 56% of the maximum speed)
// The parameter "speed" is encoded as a 8 bits (1 bytes) signed int

araffin

// From https://github.com/sergionr2/RacingRobot
// replicated in https://github.com/araffin/cpp-arduino-serial
#ifndef ORDER_H
#define ORDER_H

// Define the orders that can be sent and received
enum Order {
  HELLO = 0, // Hello order to initiate communication with the Arduino
  SERVO = 1, // Command the Servomotor (control the direction of the car)
  MOTOR = 2, // Command the Motor (control the speed of the car)

araffin

// If we have received data
if (Serial.available() > 0)
{
    // Read the order sent by the computer
    order_received = Serial.read();
    // If the received byte is the character 'a'
    if (order_received == 'a')
        // This correspond to the action GO_FORWARD
        // It will be used later to send speed order to the motor
        action = GO_FORWARD;

araffin

// Extracted from https://github.com/araffin/rust-arduino-serial
extern crate robust_arduino_serial;
use robust_arduino_serial::*;

// Open Serial Port
let mut port = serial::open(&serial_port).unwrap();
// Please see the original file to have a complete example
...
// Send the order "MOTOR", i.e. to change the speed of the car
// equivalent to write_i8(&mut port, Order::MOTOR as i8)

araffin

from stable_baselines.common.cmd_util import make_atari_env
from stable_baselines.common.policies import CnnPolicy
from stable_baselines import PPO2

# There already exists an environment generator
# that will make and wrap atari environments correctly
env = make_atari_env('DemonAttackNoFrameskip-v4', num_env=8, seed=0)

model = PPO2(CnnPolicy, env, verbose=1)
model.learn(total_timesteps=10000)

araffin

import imageio
import numpy as np

from stable_baselines.common.policies import MlpPolicy
from stable_baselines import A2C

model = A2C(MlpPolicy, "LunarLander-v2").learn(100000)

images = []                                                                                              
obs = model.env.reset()

araffin

import gym 

from stable_baselines.common.policies import MlpPolicy
from stable_baselines.common.vec_env import DummyVecEnv, VecNormalize
from stable_baselines import PPO2

env = DummyVecEnv([lambda: gym.make("Reacher-v2")])
# Automatically normalize the input features
env = VecNormalize(env, norm_obs=True, norm_reward=False,
                   clip_obs=10.)

araffin

from stable_baselines.common.cmd_util import make_atari_env
from stable_baselines.common.policies import CnnPolicy
from stable_baselines.common.vec_env import VecFrameStack
from stable_baselines import ACER

# There already exists an environment generator
# that will make and wrap atari environments correctly.
# Here we are also multiprocessing training (num_env=4 => 4 processes)
env = make_atari_env('PongNoFrameskip-v4', num_env=4, seed=0)
# Frame-stacking with 4 frames

araffin

from stable_baselines.common.policies import FeedForwardPolicy
from stable_baselines import A2C

# Custom MLP policy of three layers of size 128 each
class CustomPolicy(FeedForwardPolicy):
    def __init__(self, *args, **kwargs):
        super(CustomPolicy, self).__init__(*args, **kwargs,
                                           layers=[128, 128, 128],
                                           feature_extraction="mlp")