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

class PolicyNetwork(nn.Module):
    def __init__(self, input_dim, output_dim):
        super(PolicyNetwork, self).__init__()
        # Define the layers
        self.fc1 = nn.Linear(input_dim, 128)
        self.fc2 = nn.Linear(128, 128)
        self.fc3 = nn.Linear(128, output_dim)

    def forward(self, x):
        # Pass input through the layers with ReLU activation
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        # Output layer with softmax to get probabilities
        x = F.softmax(self.fc3(x), dim=-1)
        return x