update codes

codes/DoubleDQN/agent.py

@@ -5,7 +5,7 @@
 @Email: johnjim0816@gmail.com
 @Date: 2020-06-12 00:50:49
 @LastEditor: John
-LastEditTime: 2021-05-04 22:28:06
+LastEditTime: 2021-11-19 18:07:09
 @Discription: 
 @Environment: python 3.7.7
 '''
@@ -16,15 +16,55 @@ LastEditTime: 2021-05-04 22:28:06
 import torch
 import torch.nn as nn
 import torch.optim as optim
+import torch.nn.functional as F
 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):
+
+class ReplayBuffer:
+    def __init__(self, capacity):
+        self.capacity = capacity # 经验回放的容量
+        self.buffer = [] # 缓冲区
+        self.position = 0 
+    
+    def push(self, state, action, reward, next_state, done):
+        ''' 缓冲区是一个队列，容量超出时去掉开始存入的转移(transition)
+        '''
+        if len(self.buffer) < self.capacity:
+            self.buffer.append(None)
+        self.buffer[self.position] = (state, action, reward, next_state, done)
+        self.position = (self.position + 1) % self.capacity 
+    
+    def sample(self, batch_size):
+        batch = random.sample(self.buffer, batch_size) # 随机采出小批量转移
+        state, action, reward, next_state, done =  zip(*batch) # 解压成状态，动作等
+        return state, action, reward, next_state, done
+    
+    def __len__(self):
+        ''' 返回当前存储的量
+        '''
+        return len(self.buffer)
+
+class MLP(nn.Module):
+    def __init__(self, n_states,n_actions,hidden_dim=128):
+        """ 初始化q网络，为全连接网络
+            n_states: 输入的特征数即环境的状态数
+            n_actions: 输出的动作维度
+        """
+        super(MLP, self).__init__()
+        self.fc1 = nn.Linear(n_states, hidden_dim) # 输入层
+        self.fc2 = nn.Linear(hidden_dim,hidden_dim) # 隐藏层
+        self.fc3 = nn.Linear(hidden_dim, n_actions) # 输出层
         
-        self.action_dim = action_dim  # 总的动作个数
+    def forward(self, x):
+        # 各层对应的激活函数
+        x = F.relu(self.fc1(x)) 
+        x = F.relu(self.fc2(x))
+        return self.fc3(x)
+        
+class DoubleDQN:
+    def __init__(self, n_states, n_actions, cfg):
+        self.n_actions = n_actions  # 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
@@ -33,8 +73,8 @@ class DoubleDQN:
         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)
+        self.policy_net = MLP(n_states, n_actions,hidden_dim=cfg.hidden_dim).to(self.device)
+        self.target_net = MLP(n_states, n_actions,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)
@@ -43,8 +83,15 @@ class DoubleDQN:
         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():
+        
+    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:
+            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(
@@ -55,17 +102,8 @@ 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)
+            action = random.randrange(self.n_actions)
         return action
     def update(self):
 

codes/DoubleDQN/task0.py

@@ -0,0 +1,83 @@
+#!/usr/bin/env python
+# coding=utf-8
+'''
+Author: JiangJi
+Email: johnjim0816@gmail.com
+Date: 2021-11-07 18:10:37
+LastEditor: JiangJi
+LastEditTime: 2021-11-19 18:34:05
+Discription: 
+'''
+
+import sys,os
+curr_path = os.path.dirname(os.path.abspath(__file__)) # 当前文件所在绝对路径
+parent_path = os.path.dirname(curr_path) # 父路径
+sys.path.append(parent_path) # 添加路径到系统路径
+
+import gym
+import torch
+import datetime
+
+from common.utils import save_results, make_dir
+from common.utils import plot_rewards
+from DoubleDQN.agent import DoubleDQN
+from DoubleDQN.train import train,test
+
+curr_time = datetime.datetime.now().strftime("%Y%m%d-%H%M%S")  # 获取当前时间
+algo_name = 'DoubleDQN'  # 算法名称
+env_name = 'CartPole-v0'  # 环境名称
+class DoubleDQNConfig:
+    def __init__(self):
+        self.algo_name = algo_name # 算法名称
+        self.env_name = env_name  # 环境名称
+        self.device = torch.device(
+            "cuda" if torch.cuda.is_available() else "cpu")  # 检测GPU
+        self.train_eps = 200  # 训练的回合数
+        self.test_eps = 30  # 测试的回合数
+        self.gamma = 0.95  # 强化学习中的折扣因子
+        self.epsilon_start = 0.95  # e-greedy策略中初始epsilon
+        self.epsilon_end = 0.01  # e-greedy策略中的终止epsilon
+        self.epsilon_decay = 500  # e-greedy策略中epsilon的衰减率
+        self.lr = 0.0001  # 学习率
+        self.memory_capacity = 100000  # 经验回放的容量
+        self.batch_size = 64  # mini-batch SGD中的批量大小
+        self.target_update = 2  # 目标网络的更新频率
+        self.hidden_dim = 256  # 网络隐藏层
+class PlotConfig:
+    ''' 绘图相关参数设置
+    '''
+
+    def __init__(self) -> None:
+        self.algo_name = algo_name  # 算法名称
+        self.env_name = env_name  # 环境名称
+        self.device = torch.device(
+            "cuda" if torch.cuda.is_available() else "cpu")  # 检测GPU
+        self.result_path = curr_path + "/outputs/" + self.env_name + \
+            '/' + curr_time + '/results/'  # 保存结果的路径
+        self.model_path = curr_path + "/outputs/" + self.env_name + \
+            '/' + curr_time + '/models/'  # 保存模型的路径
+        self.save = True  # 是否保存图片
+        
+def env_agent_config(cfg,seed=1):
+    env = gym.make(cfg.env_name)  
+    env.seed(seed)
+    n_states = env.observation_space.shape[0]
+    n_actions = env.action_space.n
+    agent = DoubleDQN(n_states,n_actions,cfg)
+    return env,agent
+
+cfg = DoubleDQNConfig()
+plot_cfg = PlotConfig()
+# 训练
+env,agent = env_agent_config(cfg,seed=1)
+rewards, ma_rewards = train(cfg, env, agent)
+make_dir(plot_cfg.result_path, plot_cfg.model_path)  # 创建保存结果和模型路径的文件夹
+agent.save(path=plot_cfg.model_path)  # 保存模型
+save_results(rewards, ma_rewards, tag='train', path=plot_cfg.result_path)  # 保存结果
+plot_rewards(rewards, ma_rewards, plot_cfg, tag="train")  # 画出结果
+# 测试
+env,agent = env_agent_config(cfg,seed=10)
+agent.load(path=plot_cfg.model_path)  # 导入模型
+rewards,ma_rewards = test(cfg,env,agent)
+save_results(rewards, ma_rewards, tag='test', path=plot_cfg.result_path)  # 保存结果
+plot_rewards(rewards, ma_rewards, plot_cfg, tag="test")  # 画出结果

codes/DoubleDQN/task0_train.ipynb

@@ -1,194 +0,0 @@
-{
- "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

@@ -1,123 +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: 2021-09-10 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)

codes/DoubleDQN/train.py

@@ -0,0 +1,73 @@
+#!/usr/bin/env python
+# coding=utf-8
+'''
+Author: JiangJi
+Email: johnjim0816@gmail.com
+Date: 2021-11-07 18:10:37
+LastEditor: JiangJi
+LastEditTime: 2021-11-19 18:34:05
+Discription: 
+'''
+
+import sys,os
+curr_path = os.path.dirname(os.path.abspath(__file__)) # 当前文件所在绝对路径
+parent_path = os.path.dirname(curr_path) # 父路径
+sys.path.append(parent_path) # 添加路径到系统路径
+    
+def train(cfg,env,agent):
+    print('开始训练!')
+    print(f'环境：{cfg.env_name}, 算法：{cfg.algo_name}, 设备：{cfg.device}')
+    rewards = [] # 记录所有回合的奖励
+    ma_rewards = []  # 记录所有回合的滑动平均奖励
+    for i_ep in range(cfg.train_eps):
+        ep_reward = 0 # 记录一回合内的奖励
+        state = env.reset() # 重置环境，返回初始状态
+        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())
+        if (i_ep+1)%10 == 0: 
+            print(f'回合：{i_ep+1}/{cfg.train_eps}，奖励：{ep_reward}')
+        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('完成训练！')
+    return rewards,ma_rewards
+
+def test(cfg,env,agent):
+    print('开始测试!')
+    print(f'环境：{cfg.env_name}, 算法：{cfg.algo_name}, 设备：{cfg.device}')
+    # 由于测试不需要使用epsilon-greedy策略，所以相应的值设置为0
+    cfg.epsilon_start = 0.0 # e-greedy策略中初始epsilon
+    cfg.epsilon_end = 0.0 # e-greedy策略中的终止epsilon
+    rewards = [] # 记录所有回合的奖励
+    ma_rewards = []  # 记录所有回合的滑动平均奖励
+    for i_ep in range(cfg.test_eps):
+        state = env.reset() 
+        ep_reward = 0   
+        while True:
+            action = agent.choose_action(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"回合：{i_ep+1}/{cfg.test_eps}，奖励：{ep_reward:.1f}")
+    print('完成测试！')
+    return rewards,ma_rewards    
+