update projects

projects/codes/MonteCarlo/agent.py

@@ -5,7 +5,7 @@ Author: John
 Email: johnjim0816@gmail.com
 Date: 2021-03-12 16:14:34
 LastEditor: John
-LastEditTime: 2021-05-05 16:58:39
+LastEditTime: 2022-08-15 18:10:13
 Discription: 
 Environment: 
 '''
@@ -22,11 +22,10 @@ class FisrtVisitMC:
         self.epsilon = cfg.epsilon
         self.gamma = cfg.gamma 
         self.Q_table = defaultdict(lambda: np.zeros(n_actions))
-        self.returns_sum = defaultdict(float) # sum of returns
+        self.returns_sum = defaultdict(float) # 保存return之和
         self.returns_count = defaultdict(float)
         
-    def choose_action(self,state):
-        ''' e-greed policy '''
+    def sample(self,state):
         if state in self.Q_table.keys():
             best_action = np.argmax(self.Q_table[state])
             action_probs = np.ones(self.n_actions, dtype=float) * self.epsilon / self.n_actions
@@ -35,6 +34,15 @@ class FisrtVisitMC:
         else:
             action = np.random.randint(0,self.n_actions)
         return action
+    def predict(self,state):
+        if state in self.Q_table.keys():
+            best_action = np.argmax(self.Q_table[state])
+            action_probs = np.ones(self.n_actions, dtype=float) * self.epsilon / self.n_actions
+            action_probs[best_action] += (1.0 - self.epsilon)
+            action = np.argmax(self.Q_table[state])
+        else:
+            action = np.random.randint(0,self.n_actions)
+        return action
     def update(self,one_ep_transition):
         # Find all (state, action) pairs we've visited in this one_ep_transition
         # We convert each state to a tuple so that we can use it as a dict key
@@ -50,16 +58,18 @@ class FisrtVisitMC:
             self.returns_sum[sa_pair] += G
             self.returns_count[sa_pair] += 1.0
             self.Q_table[state][action] = self.returns_sum[sa_pair] / self.returns_count[sa_pair]
-    def save(self,path):
+    def save(self,path=None):
         '''把 Q表格 的数据保存到文件中
         '''
+        from pathlib import Path
+        Path(path).mkdir(parents=True, exist_ok=True)
         torch.save(
             obj=self.Q_table,
             f=path+"Q_table",
             pickle_module=dill
         )
 
-    def load(self, path):
+    def load(self, path=None):
         '''从文件中读取数据到 Q表格
         '''
         self.Q_table =torch.load(f=path+"Q_table",pickle_module=dill)

projects/codes/MonteCarlo/outputs/Racetrack/20220815-180742/results/params.json

@@ -0,0 +1 @@
+{"algo_name": "First-Visit MC", "env_name": "Racetrack", "train_eps": 200, "test_eps": 20, "gamma": 0.9, "epsilon": 0.15, "device": "cpu", "result_path": "/Users/jj/Desktop/rl-tutorials/codes/MonteCarlo/outputs/Racetrack/20220815-180742/results/", "model_path": "/Users/jj/Desktop/rl-tutorials/codes/MonteCarlo/outputs/Racetrack/20220815-180742/models/", "save_fig": true}

projects/codes/MonteCarlo/task0.py

@@ -0,0 +1,110 @@
+#!/usr/bin/env python
+# coding=utf-8
+'''
+Author: John
+Email: johnjim0816@gmail.com
+Date: 2021-03-11 14:26:44
+LastEditor: John
+LastEditTime: 2022-08-15 18:12:13
+Discription: 
+Environment: 
+'''
+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 datetime
+import argparse
+from common.utils import save_results,save_args,plot_rewards
+
+from MonteCarlo.agent import FisrtVisitMC
+from envs.racetrack_env import RacetrackEnv
+
+curr_time = datetime.datetime.now().strftime(
+    "%Y%m%d-%H%M%S")  # obtain current time
+
+def get_args():
+    """ 超参数
+    """
+    curr_time = datetime.datetime.now().strftime("%Y%m%d-%H%M%S") # 获取当前时间
+    parser = argparse.ArgumentParser(description="hyperparameters")      
+    parser.add_argument('--algo_name',default='First-Visit MC',type=str,help="name of algorithm")
+    parser.add_argument('--env_name',default='Racetrack',type=str,help="name of environment")
+    parser.add_argument('--train_eps',default=200,type=int,help="episodes of training")
+    parser.add_argument('--test_eps',default=20,type=int,help="episodes of testing")
+    parser.add_argument('--gamma',default=0.9,type=float,help="discounted factor")
+    parser.add_argument('--epsilon',default=0.15,type=float,help="the probability to select a random action")
+    parser.add_argument('--device',default='cpu',type=str,help="cpu or cuda") 
+    parser.add_argument('--result_path',default=curr_path + "/outputs/" + parser.parse_args().env_name + \
+            '/' + curr_time + '/results/' )
+    parser.add_argument('--model_path',default=curr_path + "/outputs/" + parser.parse_args().env_name + \
+            '/' + curr_time + '/models/' ) 
+    parser.add_argument('--show_fig',default=False,type=bool,help="if show figure or not")           
+    parser.add_argument('--save_fig',default=True,type=bool,help="if save figure or not")           
+    args = parser.parse_args()                          
+    return args
+
+def env_agent_config(cfg,seed=1):
+    env = RacetrackEnv()
+    n_actions = env.action_space.n
+    agent = FisrtVisitMC(n_actions, cfg)
+    return env,agent
+    
+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 = []
+    for i_ep in range(cfg.train_eps):
+        state = env.reset()
+        ep_reward = 0
+        one_ep_transition = []
+        while True:
+            action = agent.sample(state)
+            next_state, reward, done = env.step(action)
+            ep_reward += reward
+            one_ep_transition.append((state, action, reward))
+            state = next_state
+            if done:
+                break
+        rewards.append(ep_reward)
+        agent.update(one_ep_transition)
+        if (i_ep+1) % 10 == 0:
+            print(f"Episode:{i_ep+1}/{cfg.train_eps}: Reward:{ep_reward}")
+    print("完成训练")
+    return {'rewards':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}")
+    rewards = []
+    for i_ep in range(cfg.test_eps):
+        state = env.reset()
+        ep_reward = 0
+        while True:
+            action = agent.predict(state)
+            next_state, reward, done = env.step(action)
+            ep_reward += reward
+            state = next_state
+            if done:
+                break
+        rewards.append(ep_reward)
+        print(f'回合：{i_ep+1}/{cfg.test_eps}，奖励：{ep_reward:.2f}')
+    return {'rewards':rewards}
+    
+if __name__ == "__main__":
+    cfg = get_args()
+     # 训练
+    env, agent = env_agent_config(cfg)
+    res_dic = train(cfg, env, agent)
+    save_args(cfg,path = cfg.result_path) # 保存参数到模型路径上
+    agent.save(path = cfg.model_path)  # 保存模型
+    save_results(res_dic, tag = 'train', path = cfg.result_path)  
+    plot_rewards(res_dic['rewards'], cfg, path = cfg.result_path,tag = "train")  
+    # 测试
+    env, agent = env_agent_config(cfg) # 也可以不加，加这一行的是为了避免训练之后环境可能会出现问题，因此新建一个环境用于测试
+    agent.load(path = cfg.model_path)  # 导入模型
+    res_dic = test(cfg, env, agent)
+    save_results(res_dic, tag='test',
+                 path = cfg.result_path)  # 保存结果
+    plot_rewards(res_dic['rewards'], cfg, path = cfg.result_path,tag = "test")  # 画出结果

projects/codes/MonteCarlo/task0_train.py

@@ -1,118 +0,0 @@
-#!/usr/bin/env python
-# coding=utf-8
-'''
-Author: John
-Email: johnjim0816@gmail.com
-Date: 2021-03-11 14:26:44
-LastEditor: John
-LastEditTime: 2021-05-05 17:27:50
-Discription: 
-Environment: 
-'''
-
-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 torch
-import datetime
-
-from common.utils import save_results,make_dir
-from common.plot import plot_rewards
-from MonteCarlo.agent import FisrtVisitMC
-from envs.racetrack_env import RacetrackEnv
-
-curr_time = datetime.datetime.now().strftime(
-    "%Y%m%d-%H%M%S")  # obtain current time
-
-class MCConfig:
-    def __init__(self):
-        self.algo = "MC"  # name of algo
-        self.env = 'Racetrack'
-        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
-        # epsilon: The probability to select a random action .
-        self.epsilon = 0.15
-        self.gamma = 0.9  # gamma: Gamma discount factor.
-        self.train_eps = 200
-        self.device = torch.device(
-            "cuda" if torch.cuda.is_available() else "cpu")  # check gpu
-
-def env_agent_config(cfg,seed=1):
-    env = RacetrackEnv()
-    n_actions = 9
-    agent = FisrtVisitMC(n_actions, cfg)
-    return env,agent
-    
-def train(cfg, env, agent):
-    print('Start to eval !')
-    print(f'Env:{cfg.env}, Algorithm:{cfg.algo}, Device:{cfg.device}')
-    rewards = []
-    ma_rewards = []  # moving average rewards
-    for i_ep in range(cfg.train_eps):
-        state = env.reset()
-        ep_reward = 0
-        one_ep_transition = []
-        while True:
-            action = agent.choose_action(state)
-            next_state, reward, done = env.step(action)
-            ep_reward += reward
-            one_ep_transition.append((state, action, reward))
-            state = next_state
-            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)
-        agent.update(one_ep_transition)
-        if (i_ep+1) % 10 == 0:
-            print(f"Episode:{i_ep+1}/{cfg.train_eps}: Reward:{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 = []  # moving average 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
-            state = next_state
-            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)
-        if (i_ep+1) % 10 == 0:
-            print(f"Episode:{i_ep+1}/{cfg.train_eps}: Reward:{ep_reward}")
-    return rewards, ma_rewards
-    
-if __name__ == "__main__":
-    cfg = MCConfig()
-    
-    # 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)