model.py

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

class QNetwork(nn.Module):
    """Actor (Policy) Model."""

    def __init__(self, state_size, action_size, seed, fc1_units=64, fc2_units=64, fc3_units = 64):
        """Initialize parameters and build model.
        Params
        ======
            state_size (int): Dimension of each state
            action_size (int): Dimension of each action
            seed (int): Random seed
            fc1_units (int): Number of nodes in first hidden layer
            fc2_units (int): Number of nodes in second hidden layer
            fc3_units (int): Number of nodes in third hidden layer
            
        """
        super(QNetwork, self).__init__()
        self.seed = torch.manual_seed(seed)
        
        self.fc1 = nn.Linear(state_size, fc1_units)
        self.bn1 = nn.BatchNorm1d(fc1_units)
        self.act1 = nn.ReLU()
        self.fc2 = nn.Linear(fc1_units, fc2_units)
        self.bn2 = nn.BatchNorm1d(fc2_units)
        self.act2 = nn.ReLU()
        self.fc3 = nn.Linear(fc2_units, fc3_units)
        self.bn3 = nn.BatchNorm1d(fc3_units)
        self.act3 = nn.ReLU()
        self.fc4 = nn.Linear(fc3_units, action_size)

    def forward(self, state):
        """Build a network that maps state -> action values."""
        
        x = self.fc1(state)
        x = self.act1(x)
        x = self.bn1(x)
        x = self.fc2(x)
        x = self.act2(x)
        x = self.bn2(x)
        x = self.fc3(x)
        x = self.act3(x)
        return self.fc4(x)