import torch
import torch.optim as optim
import torch.nn.functional as F
import torch.distributions as distributions
from networks import Actor, QCritic

class QACAgent:
    def __init__(self, state_dim, action_dim, device, actor_lr=0.001, critic_lr=0.002, gamma=0.99):
        # 接收设备参数，确保网络挂载在 GPU 或 CPU 上
        self.device = device
        self.gamma = gamma
        
        # 实例化网络并移动到指定设备
        self.actor = Actor(state_dim, action_dim).to(self.device)
        self.critic = QCritic(state_dim, action_dim).to(self.device)
        
        self.actor_optimizer = optim.Adam(self.actor.parameters(), lr=actor_lr)
        self.critic_optimizer = optim.Adam(self.critic.parameters(), lr=critic_lr)

    def select_action(self, state):
        # 推理时禁用梯度图计算，加快速度
        with torch.no_grad():
            state_tensor = torch.FloatTensor(state).unsqueeze(0).to(self.device)
            action_probs = self.actor(state_tensor)
            action = distributions.Categorical(action_probs).sample().item()
        return action

    def update(self, state, action, reward, next_state, next_action, done):
        # 将数据转换为张量并送入 GPU
        state = torch.FloatTensor(state).unsqueeze(0).to(self.device)
        next_state = torch.FloatTensor(next_state).unsqueeze(0).to(self.device)
        reward = torch.FloatTensor([reward]).unsqueeze(0).to(self.device)
        
        # --- Critic 更新 ---
        q_values = self.critic(state)
        current_q = q_values[0, action]
        
        next_q_values = self.critic(next_state).detach()
        next_q = next_q_values[0, next_action]
        
        # 计算 TD 目标
        td_target = reward + self.gamma * next_q * (1 - int(done))
        critic_loss = F.mse_loss(current_q, td_target.squeeze())
        
        self.critic_optimizer.zero_grad()
        critic_loss.backward()
        self.critic_optimizer.step()
        
        # --- Actor 更新 ---
        action_probs = self.actor(state)
        dist = distributions.Categorical(action_probs)
        log_prob = dist.log_prob(torch.tensor([action]).to(self.device))
        
        # Actor 梯度上升目标：ln(pi) * Q(s, a)
        actor_loss = -(log_prob * current_q.detach())
        
        self.actor_optimizer.zero_grad()
        actor_loss.backward()
        self.actor_optimizer.step()