import torch
import torch.nn as nn
import torch.optim as optim
import numpy as np
import random
from collections import deque
import os

class DQN(nn.Module):
    def __init__(self, state_size, action_size):
        super(DQN, self).__init__()
        self.fc1 = nn.Linear(state_size, 64)
        self.fc2 = nn.Linear(64, 64)
        self.fc3 = nn.Linear(64, action_size)

    def forward(self, x):
        x = torch.relu(self.fc1(x))
        x = torch.relu(self.fc2(x))
        return self.fc3(x)

class DQNAgent:
    def __init__(self, state_size=5, action_size=4):
        self.state_size = state_size
        self.action_size = action_size
        self.memory = deque(maxlen=2000)
        self.gamma = 0.95
        self.epsilon = 1.0
        self.epsilon_min = 0.01
        self.epsilon_decay = 0.995
        self.learning_rate = 0.001
        self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
        self.model = DQN(state_size, action_size).to(self.device)
        self.optimizer = optim.Adam(self.model.parameters(), lr=self.learning_rate)
        self.criterion = nn.MSELoss()

    def get_action(self, state, explore=True):
        if explore and np.random.rand() <= self.epsilon:
            return random.randrange(self.action_size)
        
        state_t = torch.FloatTensor(state).to(self.device).unsqueeze(0)
        with torch.no_grad():
            act_values = self.model(state_t)
        return torch.argmax(act_values[0]).item()

    def remember(self, state, action, reward, next_state, done):
        self.memory.append((state, action, reward, next_state, done))

    def replay(self, batch_size):
        if len(self.memory) < batch_size:
            return
        
        minibatch = random.sample(self.memory, batch_size)
        for state, action, reward, next_state, done in minibatch:
            state_t = torch.FloatTensor(state).to(self.device)
            next_state_t = torch.FloatTensor(next_state).to(self.device)
            
            target = reward
            if not done:
                target = reward + self.gamma * torch.max(self.model(next_state_t.unsqueeze(0))[0]).item()
            
            target_f = self.model(state_t.unsqueeze(0))
            target_f[0][action] = target
            
            self.optimizer.zero_grad()
            output = self.model(state_t.unsqueeze(0))
            loss = self.criterion(output, target_f)
            loss.backward()
            self.optimizer.step()
        
        if self.epsilon > self.epsilon_min:
            self.epsilon *= self.epsilon_decay

    def save(self, path):
        os.makedirs(os.path.dirname(path), exist_ok=True)
        torch.save(self.model.state_dict(), path)

    def load(self, path):
        if os.path.exists(path):
            self.model.load_state_dict(torch.load(path, map_location=self.device))
            self.epsilon = self.epsilon_min