BaşlayınÜcretsiz Başlayın

Environment and neural network setup

You'll begin by setting up the environment you'll use throughout the course: the Lunar Lander environment, where an agent controls the thrusters for a vehicle attempting to land on the moon.

torch, torch.nn, torch.optim and gym are imported into your exercises.

Bu egzersiz

Deep Reinforcement Learning in Python

kursunun bir parçasıdır
Kursu Görüntüle

Egzersiz talimatları

  • Initialize the Lunar Lander environment in gym (LunarLander-v2).
  • Define a single linear transformation layer, with input dimension dim_inputs and output dimension dim_outputs.
  • Instantiate the Neural Network for input dimension 8 and output dimension 4.
  • Provide the Adam optimizer with the parameters.

Uygulamalı interaktif egzersiz

Bu örnek kodu tamamlayarak bu egzersizi bitirin.

# Initiate the Lunar Lander environment
env = gym.____

class Network(nn.Module):
    def __init__(self, dim_inputs, dim_outputs):
        super(Network, self).__init__()
        # Define a linear transformation layer 
        self.linear = ____
    def forward(self, x):
        return self.linear(x)

# Instantiate the network
network = ____

# Initialize the optimizer
optimizer = optim.Adam(____, lr=0.0001)

print("Network initialized as:\n", network)
Kodu Düzenle ve Çalıştır