model.py

import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F

def hidden_init(layer):
    fan_in = layer.weight.data.size()[0]
    lim = 1. / np.sqrt(fan_in)
    return (-lim, lim)

class Actor(nn.Module):
    def __init__(self, state_size, action_size, seed):

        super(Actor, self).__init__()
        self.seed = torch.manual_seed(seed)
        self.fc1 = nn.Linear(state_size, 128)
        self.bn1 = nn.BatchNorm1d(128)
        self.fc2 = nn.Linear(128, 64)
        self.fc3 = nn.Linear(64, 32)
        self.fc4 = nn.Linear(32, 16)
        self.fc5 = nn.Linear(16, action_size)
        self.reset_parameters()

    def reset_parameters(self):
        self.fc1.weight.data.uniform_(*hidden_init(self.fc1))
        self.fc2.weight.data.uniform_(*hidden_init(self.fc2))
        self.fc3.weight.data.uniform_(*hidden_init(self.fc3))
        self.fc4.weight.data.uniform_(*hidden_init(self.fc4))
        self.fc5.weight.data.uniform_(-3e-3, 3e-3)

    def forward(self, state):
        if state.dim() == 1:
            state = torch.unsqueeze(state,0)
        
        x = F.relu(self.fc1(state))
        x = self.bn1(x)
        x = F.relu(self.fc2(x))
        x = F.relu(self.fc3(x))
        x = F.relu(self.fc4(x))
        x = torch.tanh(self.fc5(x))
        
        return x

class Critic(nn.Module):
    """Critic (Value) Model."""

    def __init__(self, state_size, action_size, seed, fcs1_units=256, fc2_units=128, fc3_units=64):
        super(Critic, self).__init__()
        self.seed = torch.manual_seed(seed)
        self.fcs1 = nn.Linear(state_size, fcs1_units)
        self.bn1 = nn.BatchNorm1d(fcs1_units)
        self.fc2 = nn.Linear(fcs1_units+action_size, fc2_units)
        self.fc3 = nn.Linear(fc2_units, fc3_units)
        self.fc4 = nn.Linear(fc3_units, 1)
        self.reset_parameters()

    def reset_parameters(self):
        self.fcs1.weight.data.uniform_(*hidden_init(self.fcs1))
        self.fc2.weight.data.uniform_(*hidden_init(self.fc2))
        self.fc3.weight.data.uniform_(*hidden_init(self.fc3))
        self.fc4.weight.data.uniform_(-3e-3, 3e-3)

    def forward(self, state, action):
        xs = F.relu(self.bn1(self.fcs1(state)))
        x = torch.cat((xs, action), dim=1)
        x = F.relu(self.fc2(x))
        x = F.relu(self.fc3(x))
        return self.fc4(x)