update

codes/DoubleDQN/agent.py

@@ -5,7 +5,7 @@
 @Email: johnjim0816@gmail.com
 @Date: 2020-06-12 00:50:49
 @LastEditor: John
-LastEditTime: 2021-03-28 11:07:35
+LastEditTime: 2021-05-04 22:28:06
 @Discription: 
 @Environment: python 3.7.7
 '''
@@ -35,22 +35,16 @@ class DoubleDQN:
         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的初始模型参数完全复制policy_net
-        self.target_net.load_state_dict(self.policy_net.state_dict())
-        self.target_net.eval()  # 不启用 BatchNormalization 和 Dropout
+        # 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 choose_action(self, state):
-        '''选择动作
-        '''
-        self.epsilon = self.epsilon_end + (self.epsilon_start - self.epsilon_end) * \
-            math.exp(-1. * self.actions_count / self.epsilon_decay)
-        self.actions_count += 1
-        if random.random() > self.epsilon:
-            with torch.no_grad():
+    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(
@@ -61,6 +55,15 @@ class DoubleDQN:
                 # 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
@@ -71,7 +74,7 @@ class DoubleDQN:
         # 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)
-        ### 转为张量 ###
+        # 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(
@@ -82,8 +85,7 @@ class DoubleDQN:
             next_state_batch, device=self.device, dtype=torch.float)
         
         done_batch = torch.tensor(np.float32(
-            done_batch), device=self.device).unsqueeze(1)  # 将bool转为float然后转为张量
-
+            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)
@@ -102,7 +104,7 @@ class DoubleDQN:
             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])
+        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
@@ -113,7 +115,9 @@ class DoubleDQN:
         self.optimizer.step()  # 更新模型
 
     def save(self,path):
-        torch.save(self.target_net.state_dict(), path+'DoubleDQN_checkpoint.pth')
+        torch.save(self.target_net.state_dict(), path+'checkpoint.pth')
 
     def load(self,path):
-        self.target_net.load_state_dict(torch.load(path+'DoubleDQN_checkpoint.pth'))    
+        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/main.py

@@ -1,93 +0,0 @@
-#!/usr/bin/env python
-# coding=utf-8
-'''
-@Author: John
-@Email: johnjim0816@gmail.com
-@Date: 2020-06-12 00:48:57
-@LastEditor: John
-LastEditTime: 2021-03-28 11:05:14
-@Discription: 
-@Environment: python 3.7.7
-'''
-import sys,os
-sys.path.append(os.getcwd()) # add current terminal path
-import gym
-import torch
-import datetime
-from DoubleDQN.agent import DoubleDQN
-from common.plot import plot_rewards
-from common.utils import save_results
-
-SEQUENCE = datetime.datetime.now().strftime("%Y%m%d-%H%M%S") # 获取当前时间
-SAVED_MODEL_PATH = os.path.split(os.path.abspath(__file__))[0]+"/saved_model/"+SEQUENCE+'/' # 生成保存的模型路径
-if not os.path.exists(os.path.split(os.path.abspath(__file__))[0]+"/saved_model/"): 
-    os.mkdir(os.path.split(os.path.abspath(__file__))[0]+"/saved_model/")
-if not os.path.exists(SAVED_MODEL_PATH): 
-    os.mkdir(SAVED_MODEL_PATH)
-RESULT_PATH = os.path.split(os.path.abspath(__file__))[0]+"/results/"+SEQUENCE+'/' # 存储reward的路径
-if not os.path.exists(os.path.split(os.path.abspath(__file__))[0]+"/results/"): 
-    os.mkdir(os.path.split(os.path.abspath(__file__))[0]+"/results/")
-if not os.path.exists(RESULT_PATH): 
-    os.mkdir(RESULT_PATH)
-
-class DoubleDQNConfig:
-    def __init__(self):
-        self.algo = "Double DQN" # name of algo
-        self.gamma = 0.99
-        self.epsilon_start = 0.9 # e-greedy策略的初始epsilon
-        self.epsilon_end = 0.01
-        self.epsilon_decay = 200
-        self.lr = 0.01 # 学习率
-        self.memory_capacity = 10000 # Replay Memory容量
-        self.batch_size = 128
-        self.train_eps = 300 # 训练的episode数目
-        self.train_steps = 200 # 训练每个episode的最大长度
-        self.target_update = 2 # target net的更新频率
-        self.eval_eps = 20 # 测试的episode数目
-        self.eval_steps = 200 # 测试每个episode的最大长度
-        self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu") # 检测gpu
-        self.hidden_dim = 128 # 神经网络隐藏层维度
- 
-
-def train(cfg,env,agent):
-    print('Start to train !')
-    rewards,ma_rewards = [],[]
-    ep_steps = []
-    for i_episode in range(cfg.train_eps):
-        state = env.reset() # reset环境状态
-        ep_reward = 0
-        for i_step in range(cfg.train_steps):
-            action = agent.choose_action(state) # 根据当前环境state选择action
-            next_state, reward, done, _ = env.step(action) # 更新环境参数
-            ep_reward += reward
-            agent.memory.push(state, action, reward, next_state, done) # 将state等这些transition存入memory
-            state = next_state # 跳转到下一个状态
-            agent.update() # 每步更新网络
-            if done:
-                break
-        # 更新target network，复制DQN中的所有weights and biases
-        if i_episode % cfg.target_update == 0:
-            agent.target_net.load_state_dict(agent.policy_net.state_dict())
-        print('Episode:{}/{}, Reward:{}, Steps:{}, Done:{}'.format(i_episode+1,cfg.train_eps,ep_reward,i_step,done))
-        ep_steps.append(i_step)
-        rewards.append(ep_reward)
-        # 计算滑动窗口的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
-    
-if __name__ == "__main__":
-    cfg = DoubleDQNConfig()
-    env = gym.make('CartPole-v0').unwrapped # 可google为什么unwrapped gym，此处一般不需要
-    env.seed(1) # 设置env随机种子
-    state_dim = env.observation_space.shape[0]
-    action_dim = env.action_space.n
-    agent = DoubleDQN(state_dim,action_dim,cfg)
-    rewards,ma_rewards = train(cfg,env,agent)
-    agent.save(path=SAVED_MODEL_PATH)
-    save_results(rewards,ma_rewards,tag='train',path=RESULT_PATH)
-    plot_rewards(rewards,ma_rewards,tag="train",algo = cfg.algo,path=RESULT_PATH)

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: 2021-05-04 22:26:59
+@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()
+    # train
+    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)
+
+    # eval
+    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)

codes/DoubleDQN/utils.py

@@ -1,21 +0,0 @@
-#!/usr/bin/env python
-# coding=utf-8
-'''
-Author: John
-Email: johnjim0816@gmail.com
-Date: 2020-10-15 21:28:00
-LastEditor: John
-LastEditTime: 2020-10-15 21:50:30
-Discription: 
-Environment: 
-'''
-import os
-import numpy as np
-
-
-def save_results(rewards,moving_average_rewards,ep_steps,tag='train',result_path='./results'):
-    if not os.path.exists(result_path): # 检测是否存在文件夹
-        os.mkdir(result_path)
-    np.save(result_path+'rewards_'+tag+'.npy', rewards)
-    np.save(result_path+'moving_average_rewards_'+tag+'.npy', moving_average_rewards)
-    np.save(result_path+'steps_'+tag+'.npy',ep_steps )