araffin

"""Optuna example that optimizes the hyperparameters of
a reinforcement learning agent using PPO implementation from Stable-Baselines3
on a Gymnasium environment.

This is a simplified version of what can be found in https://github.com/DLR-RM/rl-baselines3-zoo.

You can run this example as follows:
    $ python optimize_ppo.py

"""

araffin

import matplotlib.pyplot as plt
import numpy as np
import seaborn as sns
from gymnasium import spaces
from stable_baselines3 import PPO
from stable_baselines3.common.env_util import make_vec_env
from stable_baselines3.common.vec_env import VecEnvWrapper

sns.set_theme()

araffin

# MIT License Copyright (c) 2024 Antonin Raffin
import gymnasium as gym
import numpy as np
from gymnasium.envs.mujoco.mujoco_env import MujocoEnv

# Env initialization
env = gym.make("HalfCheetah-v4", render_mode="human")
# Wrap to have reward statistics
env = gym.wrappers.RecordEpisodeStatistics(env)
mujoco_env = env.unwrapped

araffin

"""
A simple GUI to collect human feedback.
It writes the rating to a file "gui_value.txt" next to the script.
The rating can be reset by removing or emptying the text file.

Nicegui is the only dependency.
If you use `uv` you can do `uv run feedback_gui.py`.

Author: Antonin Raffin (2024)
MIT License

araffin

import sbx
import shimmy
import stable_baselines3 as sb3
from dm_control import suite
from gymnasium.wrappers import FlattenObservation
from stable_baselines3.common.env_checker import check_env

# Available envs:
# suite._DOMAINS
# suite.dog.SUITE

araffin

import gymnasium as gym
import numpy as np
from gymnasium.envs.mujoco.mujoco_env import MujocoEnv

# Env initialization
env = gym.make("Swimmer-v4", render_mode="human")
# Wrap to have reward statistics
env = gym.wrappers.RecordEpisodeStatistics(env)
mujoco_env = env.unwrapped
n_joints = 2

araffin

from __future__ import division

import cv2
import numpy as np
# Input Image
image = cv2.imread("my_image.jpg")
# Convert to HSV color space
hsv = cv2.cvtColor(image, cv2.COLOR_RGB2HSV)
# Define range of white color in HSV
lower_white = np.array([0, 0, 212])

araffin

# From https://github.com/araffin/python-arduino-serial
from robust_serial import Order, write_order, write_i8, write_i16
from robust_serial.utils import open_serial_port

# Open serial port with a baudrate of 9600 (bits/s)
serial_file = open_serial_port(baudrate=9600)

# Send the order "MOTOR", i.e. to change the speed of the car
# equivalent to write_i8(serial_file, Order.MOTOR.value)
write_order(serial_file, Order.MOTOR)

araffin

// https://github.com/datalogix/google-fonts-helper
// npm install google-fonts-helper
import { download } from 'google-fonts-helper'

const downloader = download('https://fonts.googleapis.com/css?family=Montserrat:400,700%7CRoboto:400,400italic,700%7CRoboto+Mono&display=swap', {
  base64: false,
  overwriting: false,
  outputDir: './',
  stylePath: 'fonts.css',
  fontsDir: 'fonts',

araffin

import gym

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

# Create and wrap the environment
env = gym.make('LunarLander-v2')
env = DummyVecEnv([lambda: env])