araffin

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
n_joints = 6

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

// 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
import numpy as np
import cma
from collections import OrderedDict

from stable_baselines import A2C


def flatten(params):
    """

araffin

import pytest
import numpy as np

from stable_baselines import A2C, ACER, ACKTR, DQN, DDPG, PPO1, PPO2, TRPO
from stable_baselines.common import set_global_seeds

MODEL_LIST_DISCRETE = [
    A2C,
    ACER,
    ACKTR,

araffin

tensorboard --logdir /tmp/a2c_cartpole_tensorboard/

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 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

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