update

codes/MonteCarlo/agent.py

@@ -5,13 +5,14 @@ Author: John
 Email: johnjim0816@gmail.com
 Date: 2021-03-12 16:14:34
 LastEditor: John
-LastEditTime: 2021-03-17 12:35:06
+LastEditTime: 2021-05-05 16:58:39
 Discription: 
 Environment: 
 '''
 import numpy as np
 from collections import defaultdict
 import torch
+import dill
 
 class FisrtVisitMC:
     ''' On-Policy First-Visit MC Control
@@ -20,14 +21,14 @@ class FisrtVisitMC:
         self.action_dim = action_dim
         self.epsilon = cfg.epsilon
         self.gamma = cfg.gamma 
-        self.Q = defaultdict(lambda: np.zeros(action_dim))
+        self.Q_table = defaultdict(lambda: np.zeros(action_dim))
         self.returns_sum = defaultdict(float) # sum of returns
         self.returns_count = defaultdict(float)
         
     def choose_action(self,state):
         ''' e-greed policy '''
-        if state in self.Q.keys():
-            best_action = np.argmax(self.Q[state])
+        if state in self.Q_table.keys():
+            best_action = np.argmax(self.Q_table[state])
             action_probs = np.ones(self.action_dim, dtype=float) * self.epsilon / self.action_dim
             action_probs[best_action] += (1.0 - self.epsilon)
             action = np.random.choice(np.arange(len(action_probs)), p=action_probs)
@@ -48,19 +49,17 @@ class FisrtVisitMC:
             # Calculate average return for this state over all sampled episodes
             self.returns_sum[sa_pair] += G
             self.returns_count[sa_pair] += 1.0
-            self.Q[state][action] = self.returns_sum[sa_pair] / self.returns_count[sa_pair]
+            self.Q_table[state][action] = self.returns_sum[sa_pair] / self.returns_count[sa_pair]
     def save(self,path):
         '''把 Q表格 的数据保存到文件中
         '''
-        import dill
         torch.save(
-            obj=self.Q,
-            f=path,
+            obj=self.Q_table,
+            f=path+"Q_table",
             pickle_module=dill
         )
 
     def load(self, path):
         '''从文件中读取数据到 Q表格
         '''
-        import dill
-        self.Q =torch.load(f=path,pickle_module=dill)
+        self.Q_table =torch.load(f=path+"Q_table",pickle_module=dill)

codes/MonteCarlo/main.py

@@ -1,88 +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: 2021-03-17 12:35:36
-Discription: 
-Environment: 
-'''
-import sys,os
-sys.path.append(os.getcwd())
-import argparse
-import datetime
-
-from envs.racetrack_env import RacetrackEnv
-from MonteCarlo.agent import FisrtVisitMC
-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/"): # 检测是否存在文件夹
-    os.mkdir(os.path.split(os.path.abspath(__file__))[0]+"/saved_model/")
-if not os.path.exists(SAVED_MODEL_PATH): # 检测是否存在文件夹
-    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/"): # 检测是否存在文件夹
-    os.mkdir(os.path.split(os.path.abspath(__file__))[0]+"/results/")
-if not os.path.exists(RESULT_PATH): # 检测是否存在文件夹
-    os.mkdir(RESULT_PATH)
-
-class MCConfig:
-    def __init__(self): 
-        self.epsilon = 0.15 # epsilon: The probability to select a random action . 
-        self.gamma = 0.9 # gamma: Gamma discount factor.
-        self.n_episodes = 150
-        self.n_steps = 2000
-
-def get_mc_args():
-    '''set parameters
-    '''
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--epsilon", default=0.15, type=float)  # epsilon: The probability to select a random action . float between 0 and 1.
-    parser.add_argument("--gamma", default=0.9, type=float)  # gamma: Gamma discount factor.
-    parser.add_argument("--n_episodes", default=150, type=int)
-    parser.add_argument("--n_steps", default=2000, type=int)
-    mc_cfg = parser.parse_args()
-    return mc_cfg
-
-
-
-def mc_train(cfg,env,agent):
-    rewards = []
-    ma_rewards = [] # moving average rewards
-    for i_episode in range(cfg.n_episodes):
-        one_ep_transition = []
-        state = env.reset()
-        ep_reward = 0
-        while True:
-        # for t in range(cfg.n_steps):
-            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_episode+1)%10==0:
-            print("Episode:{}/{}: Reward:{}".format(i_episode+1, mc_cfg.n_episodes,ep_reward))
-    return rewards,ma_rewards
-if __name__ == "__main__":
-    mc_cfg = MCConfig()
-    env = RacetrackEnv()
-    action_dim=9
-    agent = FisrtVisitMC(action_dim,mc_cfg)
-    rewards,ma_rewards= mc_train(mc_cfg,env,agent)
-    save_results(rewards,ma_rewards,tag='train',path=RESULT_PATH)
-    plot_rewards(rewards,ma_rewards,tag="train",algo = "On-Policy First-Visit MC Control",path=RESULT_PATH)
-    
-

codes/MonteCarlo/task0_train.py

@@ -0,0 +1,118 @@
+#!/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()
+    action_dim = 9
+    agent = FisrtVisitMC(action_dim, 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)