update

codes/PolicyGradient/agent.py

@@ -5,7 +5,7 @@ Author: John
 Email: johnjim0816@gmail.com
 Date: 2020-11-22 23:27:44
 LastEditor: John
-LastEditTime: 2021-03-13 11:50:16
+LastEditTime: 2021-03-23 16:37:14
 Discription: 
 Environment: 
 '''
@@ -13,14 +13,13 @@ import torch
 from torch.distributions import Bernoulli
 from torch.autograd import Variable
 import numpy as np
-
-from common.model import MLP1
+from PolicyGradient.model import MLP
 
 class PolicyGradient:
     
     def __init__(self, n_states,cfg):
         self.gamma = cfg.gamma
-        self.policy_net = MLP1(n_states,hidden_dim=cfg.hidden_dim)
+        self.policy_net = MLP(n_states,hidden_dim=cfg.hidden_dim)
         self.optimizer = torch.optim.RMSprop(self.policy_net.parameters(), lr=cfg.lr)
         self.batch_size = cfg.batch_size
 
@@ -66,6 +65,6 @@ class PolicyGradient:
             loss.backward()
         self.optimizer.step()
     def save_model(self,path):
-        torch.save(self.policy_net.state_dict(), path+'pg_checkpoint.pth')
+        torch.save(self.policy_net.state_dict(), path+'pg_checkpoint.pt')
     def load_model(self,path):
-        self.policy_net.load_state_dict(torch.load(path+'pg_checkpoint.pth')) 
+        self.policy_net.load_state_dict(torch.load(path+'pg_checkpoint.pt')) 

codes/PolicyGradient/main.py

@@ -5,12 +5,12 @@ Author: John
 Email: johnjim0816@gmail.com
 Date: 2020-11-22 23:21:53
 LastEditor: John
-LastEditTime: 2021-03-13 11:50:32
+LastEditTime: 2021-03-23 16:38:54
 Discription: 
 Environment: 
 '''
 import sys,os
-sys.path.append(os.getcwd()) # 添加当前终端路径
+sys.path.append(os.getcwd()) # add current terminal path to sys.path
 from itertools import count
 import datetime
 import gym
@@ -18,25 +18,25 @@ from PolicyGradient.agent import PolicyGradient
 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
+SEQUENCE = datetime.datetime.now().strftime("%Y%m%d-%H%M%S") # obtain current time
+SAVED_MODEL_PATH = os.path.split(os.path.abspath(__file__))[0]+"/saved_model/"+SEQUENCE+'/'  # path to save model
+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): # 检测是否存在文件夹
+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/"): # 检测是否存在文件夹
+RESULT_PATH = os.path.split(os.path.abspath(__file__))[0]+"/results/"+SEQUENCE+'/' # path to save rewards
+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): # 检测是否存在文件夹
+if not os.path.exists(RESULT_PATH): 
     os.mkdir(RESULT_PATH)
 
 class PGConfig:
     def __init__(self):
         self.train_eps = 300 # 训练的episode数目
         self.batch_size = 8
-        self.lr = 0.01 # 学习率
+        self.lr = 0.01 # learning rate
         self.gamma = 0.99
-        self.hidden_dim = 36 # 隐藏层维度
+        self.hidden_dim = 36 # dimmension of hidden layer
         
 def train(cfg,env,agent):
     '''下面带pool都是存放的transition序列用于gradient'''

codes/PolicyGradient/model.py

@@ -0,0 +1,30 @@
+#!/usr/bin/env python
+# coding=utf-8
+'''
+Author: John
+Email: johnjim0816@gmail.com
+Date: 2021-03-23 16:35:58
+LastEditor: John
+LastEditTime: 2021-03-23 16:36:20
+Discription: 
+Environment: 
+'''
+import torch.nn as nn
+import torch.nn.functional as F
+class MLP(nn.Module):
+    ''' 多层感知机
+        输入：state维度
+        输出：概率
+    '''
+    def __init__(self,n_states,hidden_dim = 36):
+        super(MLP, self).__init__()
+        # 24和36为hidden layer的层数，可根据state_dim, n_actions的情况来改变
+        self.fc1 = nn.Linear(n_states, hidden_dim)
+        self.fc2 = nn.Linear(hidden_dim,hidden_dim)
+        self.fc3 = nn.Linear(hidden_dim, 1)  # Prob of Left
+
+    def forward(self, x):
+        x = F.relu(self.fc1(x))
+        x = F.relu(self.fc2(x))
+        x = F.sigmoid(self.fc3(x))
+        return x