import gymnasium as gym
import torch
import torch.nn.functional as F
import numpy as np
import matplotlib.pyplot as plt
from tqdm import tqdm


class PolicyNet(torch.nn.Module):
    def __init__(self, state_dim, hidden_dim, action_dim):
        super(PolicyNet, self).__init__()
        self.fc1 = torch.nn.Linear(state_dim, hidden_dim)
        self.fc2 = torch.nn.Linear(hidden_dim, action_dim)

    def forward(self, x):
        x = F.relu(self.fc1(x))
        return F.softmax(self.fc2(x), dim=1)


class ValueNet(torch.nn.Module):
    def __init__(self, state_dim, hidden_dim):
        super(ValueNet, self).__init__()
        self.fc1 = torch.nn.Linear(state_dim, hidden_dim)
        self.fc2 = torch.nn.Linear(hidden_dim, 1)

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


def compute_advantage(gamma, lmbda, td_delta):
    td_delta = td_delta.detach().numpy()
    advantage_list = []
    advantage = 0.0
    for delta in reversed(td_delta):
        advantage = gamma * lmbda * advantage + delta
        advantage_list.append(advantage)
    advantage_list.reverse()
    return torch.tensor(np.array(advantage_list), dtype=torch.float)


class PPO:
    def __init__(self, state_dim, hidden_dim, action_dim, actor_lr, critic_lr,
                 gamma, lmbda, epochs, eps, device):
        self.actor = PolicyNet(state_dim, hidden_dim, action_dim).to(device)
        self.critic = ValueNet(state_dim, hidden_dim).to(device)
        self.actor_optimizer = torch.optim.Adam(
            self.actor.parameters(), lr=actor_lr
        )
        self.critic_optimizer = torch.optim.Adam(
            self.critic.parameters(), lr=critic_lr
        )
        self.gamma = gamma
        self.lmbda = lmbda
        self.epochs = epochs
        self.eps = eps
        self.device = device

    def take_action(self, state):
        state = np.array(state, dtype=np.float32)
        state = torch.tensor(state, dtype=torch.float).unsqueeze(0).to(
            self.device
        )
        probs = self.actor(state)
        action_dist = torch.distributions.Categorical(probs)
        action = action_dist.sample()
        return action.item()

    def update(self, transition_dict):
        states = torch.tensor(
            np.array(transition_dict['states']), dtype=torch.float
        ).to(self.device)
        actions = torch.tensor(
            np.array(transition_dict['actions']), dtype=torch.int64
        ).view(-1, 1).to(self.device)
        rewards = torch.tensor(
            np.array(transition_dict['rewards']), dtype=torch.float
        ).view(-1, 1).to(self.device)
        next_states = torch.tensor(
            np.array(transition_dict['next_states']), dtype=torch.float
        ).to(self.device)
        dones = torch.tensor(
            np.array(transition_dict['dones']), dtype=torch.float
        ).view(-1, 1).to(self.device)

        td_target = rewards + self.gamma * self.critic(next_states) * (
            1 - dones
        )
        td_delta = td_target - self.critic(states)
        advantage = compute_advantage(
            self.gamma, self.lmbda, td_delta.cpu()
        ).to(self.device)
        old_log_probs = torch.log(
            self.actor(states).gather(1, actions)
        ).detach()

        for _ in range(self.epochs):
            log_probs = torch.log(self.actor(states).gather(1, actions))
            ratio = torch.exp(log_probs - old_log_probs)
            surr1 = ratio * advantage
            surr2 = ratio.clamp(1 - self.eps, 1 + self.eps) * advantage
            actor_loss = torch.mean(-torch.min(surr1, surr2))
            critic_loss = torch.mean(
                F.mse_loss(self.critic(states), td_target.detach())
            )
            self.actor_optimizer.zero_grad()
            self.critic_optimizer.zero_grad()
            actor_loss.backward()
            critic_loss.backward()
            self.actor_optimizer.step()
            self.critic_optimizer.step()


if __name__ == '__main__':
    actor_lr = 1e-3
    critic_lr = 1e-2
    num_episodes = 500
    hidden_dim = 64
    gamma = 0.98
    lmbda = 0.95
    epochs = 10
    eps = 0.2
    device = torch.device(
        'cuda' if torch.cuda.is_available() else 'cpu'
    )

    env_name = 'CartPole-v1'
    env = gym.make(env_name)
    # env = gym.make(env_name, render_mode='human') 过程可视化
    torch.manual_seed(0)
    state_dim = env.observation_space.shape[0]
    action_dim = env.action_space.n
    agent = PPO(
        state_dim, hidden_dim, action_dim, actor_lr, critic_lr,
        gamma, lmbda, epochs, eps, device
    )

    return_list = []
    for i in range(6):
        with tqdm(total=num_episodes // 10, desc='Iteration %d' % i) as pbar:
            for episode in range(num_episodes // 10):
                episode_return = 0
                transition_dict = {
                    'states': [],
                    'actions': [],
                    'rewards': [],
                    'next_states': [],
                    'dones': []
                }
                state = env.reset()[0]
                done = False
                while not done:
                    action = agent.take_action(state)
                    next_state, reward, terminated, truncated, _ = env.step(
                        action
                    )
                    done = terminated or truncated
                    transition_dict['states'].append(state)
                    transition_dict['actions'].append(action)
                    transition_dict['rewards'].append(reward)
                    transition_dict['next_states'].append(next_state)
                    transition_dict['dones'].append(done)
                    state = next_state
                    episode_return += reward
                return_list.append(episode_return)
                agent.update(transition_dict)
                if (episode + 1) % 10 == 0:
                    pbar.set_postfix({
                        'episode': episode,
                        'return': np.mean(return_list[-10:])
                    })
                    pbar.update(1)
    episodes_list = list(range(len(return_list)))
    plt.plot(episodes_list, return_list)
    plt.xlabel('Episodes')
    plt.ylabel('Returns')
    plt.title('PPO_CartPole-v1')
    plt.show()

    state = env.reset()[0]
    for _ in range(500):
        action = agent.take_action(state)
        next_state, reward, terminated, truncated, _ = env.step(action)
        done = terminated or truncated
        state = next_state
        if done:
            state = env.reset()[0]
    env.close()