ViniTheSwan

from stable_baselines3.common.env_util import make_atari_env
from stable_baselines3.common.vec_env import VecFrameStack
from stable_baselines3 import A2C

# There already exists an environment generator
# that will make and wrap atari environments correctly.
# Here we are also multi-worker training (n_envs=4 => 4 environments)
env = make_atari_env('BreakoutNoFrameskip-v4', n_envs=16)
# Frame-stacking with 4 frames
env = VecFrameStack(env, n_stack=4)

ViniTheSwan

import gym
from stable_baselines3 import PPO

# Parallel environments
#env = make_vec_env("LunarLander-v2", n_envs=8)

# Create environment
env = gym.make('LunarLander-v2')

# Instantiate the agent

ViniTheSwan

from stable_baselines3 import PPO
from stable_baselines3.common.env_util import make_vec_env

# Parallel environments
env = make_vec_env("CartPole-v1", n_envs=4)

model = PPO("MlpPolicy", env, verbose=1)
model.learn(total_timesteps=25000)
model.save("ppo_cartpole")

ViniTheSwan

from stable_baselines3 import PPO
import gym

env = gym.make("CartPole-v1")
model = PPO(policy = "MlpPolicy",env =  env, verbose=1)
model.learn(total_timesteps=25000)

model.save("ppo_cartpole")  # saving the model to ppo_cartpole.zip
model = PPO.load("ppo_cartpole")  # loading the model from ppo_cartpole.zip

ViniTheSwan

from stable_baselines3 import PPO
import gym

# Parallel environments
env = gym.make("CartPole-v1")

model = PPO(policy = "MlpPolicy",env =  env, verbose=1)
model.learn(total_timesteps=25000)

obs = env.reset()

ViniTheSwan

# making an instance of a neuron
neuron = Perceptron(input_size = 3, learning_rate = 0.05)
#training samples
X_train = np.array([[1,0,0,1,1,0,1,0],
                    [0,1,0,1,0,1,1,0],
                    [0,0,1,0,1,1,1,0]] ) 
#training label
y_train =  np.array([  1,      0,      0,      1,    1,    0,      1,    0])
#test sample
X_test = np.array([[1],

ViniTheSwan

class Neuron:
    def __init__(self,input_size, learning_rate):
        self.w = np.random.random((input_size,1))-0.5  # self.w is a 2 dimensional column vector
        self.b  = np.random.random(1)-0.5
        self.learning_rate = learning_rate
    #forward pass
    def forward(self,x):
        a = x.T.dot(self.w) + self.b
        return a
    def loss(self,x,y):

ViniTheSwan

class Neuron:
    def __init__(self,input_size, learning_rate):
        self.w = np.random.random((input_size,1))-0.5  # self.w is a 2 dimensional column vector
        self.b  = np.random.random(1)-0.5
        self.learning_rate = learning_rate
    #forward pass
    def forward(self,x):
        y_hat = x.T.dot(self.w) + self.b
        return y_hat
    def loss(self,x,y):