import torch
import torch.nn as nn
import torch.nn.functional as F

class CNNPolicyNetwork(nn.Module):
    def __init__(self, input_channels, output_dim):
        super(CNNPolicyNetwork, self).__init__()
        # Define convolutional layers
        self.conv1 = nn.Conv2d(input_channels, 32, kernel_size=8, stride=4)
        self.conv2 = nn.Conv2d(32, 64, kernel_size=4, stride=2)
        self.conv3 = nn.Conv2d(64, 64, kernel_size=3, stride=1)
        # Define fully connected layers
        self.fc1 = nn.Linear(64 * 7 * 7, 512)
        self.fc2 = nn.Linear(512, output_dim)

    def forward(self, x):
        # Pass input through convolutional layers with ReLU activation
        x = F.relu(self.conv1(x))
        x = F.relu(self.conv2(x))
        x = F.relu(self.conv3(x))
        # Flatten the tensor before passing to fully connected layers
        x = x.view(x.size(0), -1)
        x = F.relu(self.fc1(x))
        # Output layer with softmax to get probabilities
        x = F.softmax(self.fc2(x), dim=-1)
        return x