update codes

codes/DQN/task1.py

@@ -1,3 +1,13 @@
+#!/usr/bin/env python
+# coding=utf-8
+'''
+Author: JiangJi
+Email: johnjim0816@gmail.com
+Date: 2021-12-22 11:14:17
+LastEditor: JiangJi
+LastEditTime: 2021-12-22 11:40:44
+Discription: 使用 Nature DQN 训练 CartPole-v1
+'''
 import sys
 import os
 curr_path = os.path.dirname(os.path.abspath(__file__))  # 当前文件所在绝对路径
@@ -9,9 +19,7 @@ import torch
 import datetime
 from common.utils import save_results, make_dir
 from common.utils import plot_rewards, plot_rewards_cn
-from DQN.agent import DQN
-from DQN.train import train,test
-
+from DQN.dqn import DQN
 
 curr_time = datetime.datetime.now().strftime("%Y%m%d-%H%M%S")  # 获取当前时间
 algo_name = "DQN"  # 算法名称
@@ -58,26 +66,83 @@ def env_agent_config(cfg, seed=1):
     '''
     env = gym.make(cfg.env_name)  # 创建环境
     env.seed(seed)  # 设置随机种子
-    state_dim = env.observation_space.shape[0]  # 状态数
-    action_dim = env.action_space.n  # 动作数
-    agent = DQN(state_dim, action_dim, cfg)  # 创建智能体
+    n_states = env.observation_space.shape[0]  # 状态数
+    n_actions = env.action_space.n  # 动作数
+    agent = DQN(n_states, n_actions, cfg)  # 创建智能体
     return env, agent
 
+def train(cfg, env, agent):
+    ''' 训练
+    '''
+    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) # 选择动作
+            next_state, reward, done, _ = env.step(action) # 更新环境，返回transition
+            agent.memory.push(state, action, reward, next_state, done) # 保存transition
+            state = next_state # 更新下一个状态
+            agent.update() # 更新智能体
+            ep_reward += reward # 累加奖励
+            if done:
+                break
+        if (i_ep+1) % cfg.target_update == 0: # 智能体目标网络更新
+            agent.target_net.load_state_dict(agent.policy_net.state_dict())
+        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)
+        if (i_ep+1)%10 == 0: 
+            print('回合：{}/{}, 奖励：{}'.format(i_ep+1, cfg.train_eps, ep_reward))
+    print('完成训练！')
+    return rewards, ma_rewards
 
-cfg = DQNConfig()
-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_cn(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_cn(rewards, ma_rewards, plot_cfg, tag="test")  # 画出结果
+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):
+        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) # 选择动作
+            next_state, reward, done, _ = env.step(action) # 更新环境，返回transition
+            state = next_state # 更新下一个状态
+            ep_reward += reward # 累加奖励
+            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
+if __name__ == "__main__":
+    cfg = DQNConfig()
+    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_cn(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_cn(rewards, ma_rewards, plot_cfg, tag="test")  # 画出结果