qnetwork.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, fc1_units=64,  fc2_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_unit (int): Number of nodes in first hidden layer
            fc2_unit (int): Number of nodes in second hidden layer
        """
        super(QNetwork,self).__init__()
        self.fc1 = nn.Linear(state_size, fc1_units)
        self.fc2 = nn.Linear(fc1_units, fc2_units)
        #we are just going to predict the pure reward so we can handle variable number of neighbors
        self.fc3 = nn.Linear(fc2_units, 1)
        
    def forward(self,x):
        # x = state
        """
        Build a network that maps state -> action values.
        """
        # print(f"forward, x dims {x.size()}")
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        out = self.fc3(x)
        # print(out.size())
        return out