update codes

codes/DoubleDQN/README.md

@@ -0,0 +1,39 @@
+食用本篇之前，需要有DQN算法的基础，参考[DQN算法实战](../DQN)。
+
+## 原理简介
+
+Double-DQN是2016年提出的算法，灵感源自2010年的Double-Qlearning，可参考论文[Deep Reinforcement Learning with Double Q-learning](https://arxiv.org/abs/1509.06461)。
+跟Nature DQN一样，Double-DQN也用了两个网络，一个当前网络(对应用$Q$表示)，一个目标网络(对应一般用$Q'$表示，为方便区分，以下用$Q_{tar}$代替)。我们先回忆一下，对于非终止状态，目标$Q_{tar}$值计算如下
+![在这里插入图片描述](assets/20201222145725907.png)
+
+而在Double-DQN中，不再是直接从目标$Q_{tar}$网络中选择各个动作中的最大$Q_{tar}$值，而是先从当前$Q$网络选择$Q$值最大对应的动作，然后代入到目标网络中计算对应的值：
+![在这里插入图片描述](assets/20201222150225327.png)
+Double-DQN的好处是Nature DQN中使用max虽然可以快速让Q值向可能的优化目标靠拢，但是很容易过犹不及，导致过度估计(Over Estimation)，所谓过度估计就是最终我们得到的算法模型有很大的偏差(bias)。为了解决这个问题， DDQN通过解耦目标Q值动作的选择和目标Q值的计算这两步，来达到消除过度估计的问题，感兴趣可以阅读原论文。
+
+伪代码如下：
+![在这里插入图片描述](assets/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0pvaG5KaW0w,size_16,color_FFFFFF,t_70.png)
+当然也可以两个网络可以同时为当前网络和目标网络，如下：
+![在这里插入图片描述](assets/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0pvaG5KaW0w,size_16,color_FFFFFF,t_70-20210328110837146.png)
+或者这样更好理解如何同时为当前网络和目标网络：
+![在这里插入图片描述](assets/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0pvaG5KaW0w,size_16,color_FFFFFF,t_70-20210328110837157.png)
+
+## 代码实战
+完整程序见[github](https://github.com/JohnJim0816/reinforcement-learning-tutorials/tree/master/DoubleDQN)。结合上面的原理，其实Double DQN改进来很简单，基本只需要在```update```中修改几行代码，如下：
+```python
+'''以下是Nature DQN的q_target计算方式
+next_q_state_value = self.target_net(
+next_state_batch).max(1)[0].detach()  # # 计算所有next states的Q'(s_{t+1})的最大值，Q'为目标网络的q函数,比如tensor([ 0.0060, -0.0171,...,])
+#计算 q_target
+#对于终止状态，此时done_batch[0]=1, 对应的expected_q_value等于reward
+q_target = reward_batch + self.gamma * next_q_state_value * (1-done_batch[0])
+'''
+'''以下是Double DQNq_target计算方式，与NatureDQN稍有不同'''
+next_target_values = self.target_net(
+next_state_batch)
+#选出Q(s_t‘, a)对应的action，代入到next_target_values获得target net对应的next_q_value，即Q’(s_t|a=argmax Q(s_t‘, a))
+next_target_q_value = next_target_values.gather(1, torch.max(next_q_values, 1)[1].unsqueeze(1)).squeeze(1)
+q_target = reward_batch + self.gamma * next_target_q_value * (1-done_batch[0])
+```
+reward变化结果如下：
+![在这里插入图片描述](assets/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0pvaG5KaW0w,size_16,color_FFFFFF,t_70-20210328110837128.png)
+其中下边蓝色和红色分别表示Double DQN和Nature DQN在训练中的reward变化图，而上面蓝色和绿色则表示Double DQN和Nature DQN在测试中的reward变化图。

codes/DoubleDQN/agent.py

@@ -0,0 +1,123 @@
+#!/usr/bin/env python
+# coding=utf-8
+'''
+@Author: John
+@Email: johnjim0816@gmail.com
+@Date: 2020-06-12 00:50:49
+@LastEditor: John
+LastEditTime: 2021-05-04 22:28:06
+@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 DoubleDQN:
+    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
+        # e-greedy策略相关参数
+        self.actions_count = 0
+        self.epsilon_start = cfg.epsilon_start
+        self.epsilon_end = cfg.epsilon_end
+        self.epsilon_decay = 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)
+        # target_net copy from policy_net
+        for target_param, param in zip(self.target_net.parameters(), self.policy_net.parameters()):
+            target_param.data.copy_(param.data)
+        # self.target_net.eval()  # 不启用 BatchNormalization 和 Dropout
+        # 可查parameters()与state_dict()的区别，前者require_grad=True
+        self.optimizer = optim.Adam(self.policy_net.parameters(), lr=cfg.lr)
+        self.loss = 0
+        self.memory = ReplayBuffer(cfg.memory_capacity)
+    def predict(self,state):
+        with torch.no_grad():
+                # 先转为张量便于丢给神经网络,state元素数据原本为float64
+                # 注意state=torch.tensor(state).unsqueeze(0)跟state=torch.tensor([state])等价
+                state = torch.tensor(
+                    [state], device=self.device, dtype=torch.float32)
+                # 如tensor([[-0.0798, -0.0079]], grad_fn=<AddmmBackward>)
+                q_value = self.policy_net(state)
+                # tensor.max(1)返回每行的最大值以及对应的下标，
+                # 如torch.return_types.max(values=tensor([10.3587]),indices=tensor([0]))
+                # 所以tensor.max(1)[1]返回最大值对应的下标，即action
+                action = q_value.max(1)[1].item()  
+        return action
+    def choose_action(self, state):
+        '''选择动作
+        '''
+        self.actions_count += 1
+        self.epsilon = self.epsilon_end + (self.epsilon_start - self.epsilon_end) * \
+            math.exp(-1. * self.actions_count / self.epsilon_decay)
+        if random.random() > self.epsilon:
+            action  = self.predict(state)
+        else:
+            action = random.randrange(self.action_dim)
+        return action
+    def update(self):
+
+        if len(self.memory) < self.batch_size:
+            return
+        # 从memory中随机采样transition
+        state_batch, action_batch, reward_batch, next_state_batch, done_batch = self.memory.sample(
+            self.batch_size)
+        # convert to tensor
+        state_batch = torch.tensor(
+            state_batch, device=self.device, dtype=torch.float)
+        action_batch = torch.tensor(action_batch, device=self.device).unsqueeze(
+            1)  # 例如tensor([[1],...,[0]])
+        reward_batch = torch.tensor(
+            reward_batch, device=self.device, dtype=torch.float)  # tensor([1., 1.,...,1])
+        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)  # 将bool转为float然后转为张量
+        # 计算当前(s_t,a)对应的Q(s_t, a)
+        q_values = self.policy_net(state_batch) 
+        next_q_values = self.policy_net(next_state_batch)
+        # 代入当前选择的action，得到Q(s_t|a=a_t)
+        q_value = q_values.gather(dim=1, index=action_batch)
+        '''以下是Nature DQN的q_target计算方式
+        # 计算所有next states的Q'(s_{t+1})的最大值，Q'为目标网络的q函数
+        next_q_state_value = self.target_net(
+            next_state_batch).max(1)[0].detach()  # 比如tensor([ 0.0060, -0.0171,...,])
+        # 计算 q_target
+        # 对于终止状态，此时done_batch[0]=1, 对应的expected_q_value等于reward
+        q_target = reward_batch + self.gamma * next_q_state_value * (1-done_batch[0])
+        '''
+        '''以下是Double DQN q_target计算方式，与NatureDQN稍有不同'''
+        next_target_values = self.target_net(
+            next_state_batch)
+        # 选出Q(s_t‘, a)对应的action，代入到next_target_values获得target net对应的next_q_value，即Q’(s_t|a=argmax Q(s_t‘, a))
+        next_target_q_value = next_target_values.gather(1, torch.max(next_q_values, 1)[1].unsqueeze(1)).squeeze(1)
+        q_target = reward_batch + self.gamma * next_target_q_value * (1-done_batch)
+        self.loss = nn.MSELoss()(q_value, q_target.unsqueeze(1))  # 计算 均方误差loss
+        # 优化模型
+        self.optimizer.zero_grad()  # zero_grad清除上一步所有旧的gradients from the last step
+        # loss.backward()使用backpropagation计算loss相对于所有parameters(需要gradients)的微分
+        self.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()  # 更新模型
+
+    def save(self,path):
+        torch.save(self.target_net.state_dict(), path+'checkpoint.pth')
+
+    def load(self,path):
+        self.target_net.load_state_dict(torch.load(path+'checkpoint.pth'))  
+        for target_param, param in zip(self.target_net.parameters(), self.policy_net.parameters()):
+            param.data.copy_(target_param.data)  

codes/DoubleDQN/task0_train.ipynb

@@ -0,0 +1,194 @@
+{
+ "metadata": {
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.10"
+  },
+  "orig_nbformat": 2,
+  "kernelspec": {
+   "name": "python3710jvsc74a57bd0366e1054dee9d4501b0eb8f87335afd3c67fc62db6ee611bbc7f8f5a1fefe232",
+   "display_name": "Python 3.7.10 64-bit ('py37': conda)"
+  },
+  "metadata": {
+   "interpreter": {
+    "hash": "366e1054dee9d4501b0eb8f87335afd3c67fc62db6ee611bbc7f8f5a1fefe232"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2,
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import sys\n",
+    "from pathlib import Path\n",
+    "curr_path = str(Path().absolute())\n",
+    "parent_path = str(Path().absolute().parent)\n",
+    "sys.path.append(parent_path) # add current terminal path to sys.path"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import gym\n",
+    "import torch\n",
+    "import datetime\n",
+    "from DoubleDQN.agent import DoubleDQN\n",
+    "from common.plot import plot_rewards\n",
+    "from common.utils import save_results, make_dir\n",
+    "\n",
+    "curr_time = datetime.datetime.now().strftime(\n",
+    "    \"%Y%m%d-%H%M%S\")  # obtain current time"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class DoubleDQNConfig:\n",
+    "    def __init__(self):\n",
+    "        self.algo = \"DoubleDQN\" # name of algo\n",
+    "        self.env = 'CartPole-v0'  # env name\n",
+    "        self.result_path = curr_path+\"/outputs/\" + self.env + \\\n",
+    "            '/'+curr_time+'/results/'  # path to save results\n",
+    "        self.model_path = curr_path+\"/outputs/\" + self.env + \\\n",
+    "            '/'+curr_time+'/models/'  # path to save models\n",
+    "        self.train_eps = 200 # max tranng episodes\n",
+    "        self.eval_eps = 50 # max evaling episodes\n",
+    "        self.gamma = 0.95\n",
+    "        self.epsilon_start = 1 # start epsilon of e-greedy policy\n",
+    "        self.epsilon_end = 0.01 \n",
+    "        self.epsilon_decay = 500\n",
+    "        self.lr = 0.001 # learning rate\n",
+    "        self.memory_capacity = 100000 # capacity of Replay Memory\n",
+    "        self.batch_size = 64\n",
+    "        self.target_update = 2 # update frequency of target net\n",
+    "        self.device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\") # check gpu\n",
+    "        self.hidden_dim = 256 # hidden size of net"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def env_agent_config(cfg,seed=1):\n",
+    "    env = gym.make(cfg.env)  \n",
+    "    env.seed(seed)\n",
+    "    state_dim = env.observation_space.shape[0]\n",
+    "    action_dim = env.action_space.n\n",
+    "    agent = DoubleDQN(state_dim,action_dim,cfg)\n",
+    "    return env,agent"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def train(cfg,env,agent):\n",
+    "    print('Start to train !')\n",
+    "    rewards,ma_rewards = [],[]\n",
+    "    for i_ep in range(cfg.train_eps):\n",
+    "        state = env.reset() \n",
+    "        ep_reward = 0\n",
+    "        while True:\n",
+    "            action = agent.choose_action(state) \n",
+    "            next_state, reward, done, _ = env.step(action)\n",
+    "            ep_reward += reward\n",
+    "            agent.memory.push(state, action, reward, next_state, done) \n",
+    "            state = next_state \n",
+    "            agent.update() \n",
+    "            if done:\n",
+    "                break\n",
+    "        if i_ep % cfg.target_update == 0:\n",
+    "            agent.target_net.load_state_dict(agent.policy_net.state_dict())\n",
+    "        if (i_ep+1)%10 == 0:\n",
+    "            print(f'Episode:{i_ep+1}/{cfg.train_eps}, Reward:{ep_reward}')\n",
+    "        rewards.append(ep_reward)\n",
+    "        if ma_rewards:\n",
+    "            ma_rewards.append(\n",
+    "                0.9*ma_rewards[-1]+0.1*ep_reward)\n",
+    "        else:\n",
+    "            ma_rewards.append(ep_reward)   \n",
+    "    print('Complete training！')\n",
+    "    return rewards,ma_rewards"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def eval(cfg,env,agent):\n",
+    "    print('Start to eval !')\n",
+    "    print(f'Env:{cfg.env}, Algorithm:{cfg.algo}, Device:{cfg.device}')\n",
+    "    rewards = []  \n",
+    "    ma_rewards = []\n",
+    "    for i_ep in range(cfg.eval_eps):\n",
+    "        state = env.reset() \n",
+    "        ep_reward = 0   \n",
+    "        while True:\n",
+    "            action = agent.predict(state)  \n",
+    "            next_state, reward, done, _ = env.step(action)  \n",
+    "            state = next_state  \n",
+    "            ep_reward += reward\n",
+    "            if done:\n",
+    "                break\n",
+    "        rewards.append(ep_reward)\n",
+    "        if ma_rewards:\n",
+    "            ma_rewards.append(ma_rewards[-1]*0.9+ep_reward*0.1)\n",
+    "        else:\n",
+    "            ma_rewards.append(ep_reward)\n",
+    "        print(f\"Episode:{i_ep+1}/{cfg.eval_eps}, reward:{ep_reward:.1f}\")\n",
+    "    print('Complete evaling！')\n",
+    "    return rewards,ma_rewards "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "if __name__ == \"__main__\":\n",
+    "    cfg = DoubleDQNConfig()\n",
+    "    # train\n",
+    "    env,agent = env_agent_config(cfg,seed=1)\n",
+    "    rewards, ma_rewards = train(cfg, env, agent)\n",
+    "    make_dir(cfg.result_path, cfg.model_path)\n",
+    "    agent.save(path=cfg.model_path)\n",
+    "    save_results(rewards, ma_rewards, tag='train', path=cfg.result_path)\n",
+    "    plot_rewards(rewards, ma_rewards, tag=\"train\",\n",
+    "                 algo=cfg.algo, path=cfg.result_path)\n",
+    "\n",
+    "    # eval\n",
+    "    env,agent = env_agent_config(cfg,seed=10)\n",
+    "    agent.load(path=cfg.model_path)\n",
+    "    rewards,ma_rewards = eval(cfg,env,agent)\n",
+    "    save_results(rewards,ma_rewards,tag='eval',path=cfg.result_path)\n",
+    "    plot_rewards(rewards,ma_rewards,tag=\"eval\",env=cfg.env,algo = cfg.algo,path=cfg.result_path)"
+   ]
+  }
+ ]
+}

codes/DoubleDQN/task0_train.py

@@ -0,0 +1,123 @@
+#!/usr/bin/env python
+# coding=utf-8
+'''
+@Author: John
+@Email: johnjim0816@gmail.com
+@Date: 2020-06-12 00:48:57
+@LastEditor: John
+LastEditTime: 2021-09-10 15:26:05
+@Discription: 
+@Environment: python 3.7.7
+'''
+import sys,os
+curr_path = os.path.dirname(__file__)
+parent_path = os.path.dirname(curr_path)
+sys.path.append(parent_path)  # add current terminal path to sys.path
+
+import gym
+import torch
+import datetime
+from DoubleDQN.agent import DoubleDQN
+from common.plot import plot_rewards
+from common.utils import save_results, make_dir
+
+curr_time = datetime.datetime.now().strftime(
+    "%Y%m%d-%H%M%S")  # obtain current time
+
+class DoubleDQNConfig:
+    def __init__(self):
+        self.algo = "DoubleDQN" # name of algo
+        self.env = 'CartPole-v0'  # env name
+        self.result_path = curr_path+"/outputs/" + self.env + \
+            '/'+curr_time+'/results/'  # path to save results
+        self.model_path = curr_path+"/outputs/" + self.env + \
+            '/'+curr_time+'/models/'  # path to save models
+        self.train_eps = 200 # max tranng episodes
+        self.eval_eps = 50 # max evaling episodes
+        self.gamma = 0.95
+        self.epsilon_start = 1 # start epsilon of e-greedy policy
+        self.epsilon_end = 0.01 
+        self.epsilon_decay = 500
+        self.lr = 0.001 # learning rate
+        self.memory_capacity = 100000 # capacity of Replay Memory
+        self.batch_size = 64
+        self.target_update = 2 # update frequency of target net
+        self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu") # check gpu
+        self.hidden_dim = 256 # hidden size of net
+ 
+def env_agent_config(cfg,seed=1):
+    env = gym.make(cfg.env)  
+    env.seed(seed)
+    state_dim = env.observation_space.shape[0]
+    action_dim = env.action_space.n
+    agent = DoubleDQN(state_dim,action_dim,cfg)
+    return env,agent
+    
+def train(cfg,env,agent):
+    print('Start to train !')
+    rewards,ma_rewards = [],[]
+    for i_ep in range(cfg.train_eps):
+        state = env.reset() 
+        ep_reward = 0
+        while True:
+            action = agent.choose_action(state) 
+            next_state, reward, done, _ = env.step(action)
+            ep_reward += reward
+            agent.memory.push(state, action, reward, next_state, done) 
+            state = next_state 
+            agent.update() 
+            if done:
+                break
+        if i_ep % cfg.target_update == 0:
+            agent.target_net.load_state_dict(agent.policy_net.state_dict())
+        print(f'Episode:{i_ep+1}/{cfg.train_eps}, Reward:{ep_reward},Epsilon:{agent.epsilon:.2f}')
+        rewards.append(ep_reward)
+        if ma_rewards:
+            ma_rewards.append(
+                0.9*ma_rewards[-1]+0.1*ep_reward)
+        else:
+            ma_rewards.append(ep_reward)   
+    print('Complete training！')
+    return rewards,ma_rewards
+
+def eval(cfg,env,agent):
+    print('Start to eval !')
+    print(f'Env:{cfg.env}, Algorithm:{cfg.algo}, Device:{cfg.device}')
+    rewards = []  
+    ma_rewards = []
+    for i_ep in range(cfg.eval_eps):
+        state = env.reset() 
+        ep_reward = 0   
+        while True:
+            action = agent.predict(state)  
+            next_state, reward, done, _ = env.step(action)  
+            state = next_state  
+            ep_reward += reward
+            if done:
+                break
+        rewards.append(ep_reward)
+        if ma_rewards:
+            ma_rewards.append(ma_rewards[-1]*0.9+ep_reward*0.1)
+        else:
+            ma_rewards.append(ep_reward)
+        print(f"Episode:{i_ep+1}/{cfg.eval_eps}, reward:{ep_reward:.1f}")
+    print('Complete evaling！')
+    return rewards,ma_rewards    
+    
+if __name__ == "__main__":
+    cfg = DoubleDQNConfig()
+    # 训练
+    env,agent = env_agent_config(cfg,seed=1)
+    rewards, ma_rewards = train(cfg, env, agent)
+    make_dir(cfg.result_path, cfg.model_path)
+    agent.save(path=cfg.model_path)
+    save_results(rewards, ma_rewards, tag='train', path=cfg.result_path)
+    plot_rewards(rewards, ma_rewards, tag="train",
+                 algo=cfg.algo, path=cfg.result_path)
+
+    # 测试
+    env,agent = env_agent_config(cfg,seed=10)
+    agent.load(path=cfg.model_path)
+    rewards,ma_rewards = eval(cfg,env,agent)
+    save_results(rewards,ma_rewards,tag='eval',path=cfg.result_path)
+    plot_rewards(rewards,ma_rewards,tag="eval",env=cfg.env,algo = cfg.algo,path=cfg.result_path)