import numpy as np
import torch
import torch.nn.functional as F
from torch.distributions import Normal
from networks import PolicyNetwork, ValueNetwork


class PPOAgent:
    """
    PPO-Clip (Proximal Policy Optimization, Clipped version)

    Reference: Schulman et al., "Proximal Policy Optimization Algorithms", 2017.

    与 TRPO 的核心区别：
    - 不再使用共轭梯度 + 线搜索求解约束优化
    - 用 clip(ratio, 1-ε, 1+ε) 限制策略更新幅度
    - 支持多 epoch 的小批量更新（每次从经验池中采样）
    """

    def __init__(
        self,
        state_dim,
        action_dim,
        action_bound,
        hidden_dim=128,
        gamma=0.99,
        tau=0.97,
        lr=3e-4,
        clip_eps=0.2,
        k_epochs=10,
        minibatch_size=64,
        critic_epochs=10,
        entropy_coef=0.0,
    ):
        self.gamma = gamma
        self.tau = tau
        self.clip_eps = clip_eps        # PPO-Clip 的裁剪范围 ε
        self.k_epochs = k_epochs         # 每次更新对同一批数据的训练轮数
        self.minibatch_size = minibatch_size
        self.entropy_coef = entropy_coef # 熵正则化系数（可选，鼓励探索）

        self.actor = PolicyNetwork(state_dim, action_dim, action_bound, hidden_dim)
        self.critic = ValueNetwork(state_dim, hidden_dim)

        self.actor_optimizer = torch.optim.Adam(self.actor.parameters(), lr=lr)
        self.critic_optimizer = torch.optim.Adam(self.critic.parameters(), lr=lr)

    def get_action(self, state):
        state_tensor = torch.FloatTensor(state).unsqueeze(0)
        with torch.no_grad():
            dist = self.actor.evaluate(state_tensor)
            action = dist.sample()
        return action.squeeze(0).numpy()

    def _compute_advantages(self, rewards, values, masks):
        """
        GAE (Generalized Advantage Estimation)
        """
        returns = []
        gae = 0
        for i in reversed(range(len(rewards))):
            delta = rewards[i] + self.gamma * values[i + 1] * masks[i] - values[i]
            gae = delta + self.gamma * self.tau * masks[i] * gae
            returns.insert(0, gae + values[i])
        return returns

    def update(self, memory):
        """
        PPO-Clip 更新

        Algorithm 1 (Schulman et al. 2017):
          for iteration=1, 2, ... do
            for actor=1, 2, ..., N do
              Run policy π_θold in environment for T timesteps
              Compute advantage estimates Aˆ1, ..., AˆT
            end for
            Optimize surrogate L wrt θ, with K epochs and minibatch size M ≤ NT
            θold ← θ
          end for
        """
        # ---------- 1. 准备数据 ----------
        states = torch.FloatTensor(np.array([m[0] for m in memory]))
        actions = torch.FloatTensor(np.array([m[1] for m in memory]))
        rewards = [m[2] for m in memory]
        next_states = torch.FloatTensor(np.array([m[3] for m in memory]))
        masks = [m[4] for m in memory]

        # ---------- 2. GAE 优势估计 ----------
        with torch.no_grad():
            values = self.critic(states).squeeze().numpy().tolist()
            next_value = self.critic(next_states[-1].unsqueeze(0)).squeeze().item()
            values.append(next_value)

        returns = self._compute_advantages(rewards, values, masks)
        returns = torch.FloatTensor(returns)
        values = torch.FloatTensor(values[:-1])
        advantages = returns - values
        advantages = (advantages - advantages.mean()) / (advantages.std() + 1e-8)

        # ---------- 3. 训练 Critic (Value Network) ----------
        for _ in range(self.critic_epochs):
            critic_loss = F.mse_loss(self.critic(states).squeeze(), returns)
            self.critic_optimizer.zero_grad()
            critic_loss.backward()
            self.critic_optimizer.step()

        # ---------- 4. 训练 Actor (PPO-Clip 损失) ----------
        # 在 no_grad 下记录旧策略的对数概率（对应 Algorithm 1 中的 π_θold）
        with torch.no_grad():
            old_dist = self.actor.evaluate(states)
            old_log_probs = old_dist.log_prob(actions).sum(dim=1)

        dataset_size = states.size(0)
        indices = np.arange(dataset_size)

        for _ in range(self.k_epochs):
            # 每轮随机打乱，分成多个 minibatch
            np.random.shuffle(indices)

            for start in range(0, dataset_size, self.minibatch_size):
                end = start + self.minibatch_size
                mb_idx = indices[start:end]

                mb_states = states[mb_idx]
                mb_actions = actions[mb_idx]
                mb_advantages = advantages[mb_idx]
                mb_old_log_probs = old_log_probs[mb_idx]

                # 当前策略的对数概率
                dist = self.actor.evaluate(mb_states)
                log_probs = dist.log_prob(mb_actions).sum(dim=1)

                # 概率比 r_t(θ) = π_θ(a|s) / π_θold(a|s)
                ratio = torch.exp(log_probs - mb_old_log_probs)

                # ---------- PPO-Clip 核心 ----------
                # L^CLIP(θ) = E[min(r_t(θ) * A_t, clip(r_t(θ), 1-ε, 1+ε) * A_t)]
                surr1 = ratio * mb_advantages
                surr2 = torch.clamp(ratio, 1 - self.clip_eps, 1 + self.clip_eps) * mb_advantages
                policy_loss = -torch.min(surr1, surr2).mean()
                # ---------------------------------

                # 可选：熵正则化（鼓励探索）
                entropy_loss = -self.entropy_coef * dist.entropy().mean() if self.entropy_coef > 0 else 0

                total_loss = policy_loss + entropy_loss

                self.actor_optimizer.zero_grad()
                total_loss.backward()
                self.actor_optimizer.step()