#!/usr/bin/env python
# coding=utf-8
'''
@Author: John
@Email: johnjim0816@gmail.com
@Date: 2020-06-12 00:50:49
@LastEditor: John
LastEditTime: 2021-09-15 13:35:36
@Discription: 
@Environment: python 3.7.7
'''
'''off-policy
'''




import torch
import torch.nn as nn
import torch.optim as optim
import random
import math
import numpy as np
from common.memory import ReplayBuffer
from common.model import MLP
class DQN:
    def __init__(self, state_dim, action_dim, cfg):

        self.action_dim = action_dim  # 总的动作个数
        self.device = cfg.device  # 设备，cpu或gpu等
        self.gamma = cfg.gamma  # 奖励的折扣因子
        # e-greedy策略相关参数
        self.frame_idx = 0  # 用于epsilon的衰减计数
        self.epsilon = lambda frame_idx: cfg.epsilon_end + \
            (cfg.epsilon_start - cfg.epsilon_end) * \
            math.exp(-1. * frame_idx / cfg.epsilon_decay)
        self.batch_size = cfg.batch_size
        self.policy_net = MLP(state_dim, action_dim,hidden_dim=cfg.hidden_dim).to(self.device)
        self.target_net = MLP(state_dim, action_dim,hidden_dim=cfg.hidden_dim).to(self.device)
        for target_param, param in zip(self.target_net.parameters(),self.policy_net.parameters()): # 复制参数到目标网路targe_net
            target_param.data.copy_(param.data)
        self.optimizer = optim.Adam(self.policy_net.parameters(), lr=cfg.lr) # 优化器
        self.memory = ReplayBuffer(cfg.memory_capacity)

    def choose_action(self, state):
        '''选择动作
        '''
        self.frame_idx += 1
        if random.random() > self.epsilon(self.frame_idx):
            with torch.no_grad():
                state = torch.tensor([state], device=self.device, dtype=torch.float32)
                q_values = self.policy_net(state)
                action = q_values.max(1)[1].item() # 选择Q值最大的动作
        else:
            action = random.randrange(self.action_dim)
        return action
    def predict(self,state):
        with torch.no_grad():
            state = torch.tensor([state], device=self.device, dtype=torch.float32)
            q_values = self.policy_net(state)
            action = q_values.max(1)[1].item()
        return action
    def update(self):
        if len(self.memory) < self.batch_size: # 当memory中不满足一个批量时，不更新策略
            return
        # 从经验回放中(replay memory)中随机采样一个批量的转移(transition)
        state_batch, action_batch, reward_batch, next_state_batch, done_batch = self.memory.sample(
            self.batch_size)
        # 转为张量
        state_batch = torch.tensor(
            state_batch, device=self.device, dtype=torch.float)
        action_batch = torch.tensor(action_batch, device=self.device).unsqueeze(
            1)  
        reward_batch = torch.tensor(
            reward_batch, device=self.device, dtype=torch.float)  
        next_state_batch = torch.tensor(
            next_state_batch, device=self.device, dtype=torch.float)
        done_batch = torch.tensor(np.float32(
            done_batch), device=self.device)
        q_values = self.policy_net(state_batch).gather(dim=1, index=action_batch) # 计算当前状态(s_t,a)对应的Q(s_t, a)
        next_q_values = self.target_net(next_state_batch).max(1)[0].detach() # 计算下一时刻的状态(s_t_,a)对应的Q值
        # 计算期望的Q值，对于终止状态，此时done_batch[0]=1, 对应的expected_q_value等于reward
        expected_q_values = reward_batch + self.gamma * next_q_values * (1-done_batch)
        loss = nn.MSELoss()(q_values, expected_q_values.unsqueeze(1))  # 计算均方根损失
        # 优化更新模型
        self.optimizer.zero_grad()  
        loss.backward()
        for param in self.policy_net.parameters():  # clip防止梯度爆炸
            param.grad.data.clamp_(-1, 1)
        self.optimizer.step() 

    def save(self, path):
        torch.save(self.target_net.state_dict(), path+'dqn_checkpoint.pth')

    def load(self, path):
        self.target_net.load_state_dict(torch.load(path+'dqn_checkpoint.pth'))
        for target_param, param in zip(self.target_net.parameters(), self.policy_net.parameters()):
            param.data.copy_(target_param.data)