update codes

codes/common/model.py

@@ -15,15 +15,15 @@ import torch.nn.functional as F
 from torch.distributions import Categorical
 
 class MLP(nn.Module):
-    def __init__(self, input_dim,output_dim,hidden_dim=128):
+    def __init__(self, n_states,n_actions,hidden_dim=128):
         """ 初始化q网络，为全连接网络
-            input_dim: 输入的特征数即环境的状态数
-            output_dim: 输出的动作维度
+            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(input_dim, hidden_dim) # 输入层
+        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, output_dim) # 输出层
+        self.fc3 = nn.Linear(hidden_dim, n_actions) # 输出层
         
     def forward(self, x):
         # 各层对应的激活函数
@@ -32,10 +32,10 @@ class MLP(nn.Module):
         return self.fc3(x)
 
 class Critic(nn.Module):
-    def __init__(self, n_obs, output_dim, hidden_size, init_w=3e-3):
+    def __init__(self, n_obs, n_actions, hidden_size, init_w=3e-3):
         super(Critic, self).__init__()
         
-        self.linear1 = nn.Linear(n_obs + output_dim, hidden_size)
+        self.linear1 = nn.Linear(n_obs + n_actions, hidden_size)
         self.linear2 = nn.Linear(hidden_size, hidden_size)
         self.linear3 = nn.Linear(hidden_size, 1)
         # 随机初始化为较小的值
@@ -51,11 +51,11 @@ class Critic(nn.Module):
         return x
 
 class Actor(nn.Module):
-    def __init__(self, n_obs, output_dim, hidden_size, init_w=3e-3):
+    def __init__(self, n_obs, n_actions, hidden_size, init_w=3e-3):
         super(Actor, self).__init__()  
         self.linear1 = nn.Linear(n_obs, hidden_size)
         self.linear2 = nn.Linear(hidden_size, hidden_size)
-        self.linear3 = nn.Linear(hidden_size, output_dim)
+        self.linear3 = nn.Linear(hidden_size, n_actions)
         
         self.linear3.weight.data.uniform_(-init_w, init_w)
         self.linear3.bias.data.uniform_(-init_w, init_w)
@@ -67,18 +67,18 @@ class Actor(nn.Module):
         return x
 
 class ActorCritic(nn.Module):
-    def __init__(self, input_dim, output_dim, hidden_dim=256):
+    def __init__(self, n_states, n_actions, hidden_dim=256):
         super(ActorCritic, self).__init__()
         self.critic = nn.Sequential(
-            nn.Linear(input_dim, hidden_dim),
+            nn.Linear(n_states, hidden_dim),
             nn.ReLU(),
             nn.Linear(hidden_dim, 1)
         )
         
         self.actor = nn.Sequential(
-            nn.Linear(input_dim, hidden_dim),
+            nn.Linear(n_states, hidden_dim),
             nn.ReLU(),
-            nn.Linear(hidden_dim, output_dim),
+            nn.Linear(hidden_dim, n_actions),
             nn.Softmax(dim=1),
         )
         

codes/common/plot.py

@@ -11,36 +11,52 @@ Environment:
 '''
 import matplotlib.pyplot as plt
 import seaborn as sns
-from matplotlib.font_manager import FontProperties
-def chinese_font():  
-    return FontProperties(fname='/System/Library/Fonts/STHeiti Light.ttc',size=15)  # 系统字体路径，此处是mac的
-def plot_rewards(rewards,ma_rewards,tag="train",env='CartPole-v0',algo = "DQN",save=True,path='./'):
-    sns.set()
-    plt.title("average learning curve of {} for {}".format(algo,env))
+# from matplotlib.font_manager import FontProperties # 导入字体模块
+
+# def chinese_font():  
+#     ''' 设置中文字体
+#     '''
+#     return FontProperties(fname='/System/Library/Fonts/STHeiti Light.ttc',size=15)  # fname系统字体路径，此处是mac的
+# def plot_rewards_cn(rewards,ma_rewards,tag="train",env='CartPole-v0',algo = "DQN",save=True,path='./'):
+#     ''' 中文画图
+#     '''
+#     sns.set()
+#     plt.figure()
+#     plt.title(u"{}环境下{}算法的学习曲线".format(env,algo),fontproperties=chinese_font())
+#     plt.xlabel(u'回合数',fontproperties=chinese_font())
+#     plt.plot(rewards)
+#     plt.plot(ma_rewards)
+#     plt.legend((u'奖励',u'滑动平均奖励',),loc="best",prop=chinese_font())
+#     if save:
+#         plt.savefig(path+f"{tag}_rewards_curve_cn")
+#     # plt.show()
+
+def plot_rewards(rewards,ma_rewards,plot_cfg,tag='train'):
+    sns.set() 
+    plt.figure() # 创建一个图形实例，方便同时多画几个图
+    plt.title("learning curve on {} of {} for {}".format(plot_cfg.device, plot_cfg.algo, plot_cfg.env))
     plt.xlabel('epsiodes')
     plt.plot(rewards,label='rewards')
     plt.plot(ma_rewards,label='ma rewards')
     plt.legend()
-    if save:
-        plt.savefig(path+"{}_rewards_curve".format(tag))
+    if plot_cfg.save:
+        plt.savefig(plot_cfg.result_path+"{}_rewards_curve".format(tag))
     plt.show()
-
-def plot_rewards_cn(rewards,ma_rewards,tag="train",env='CartPole-v0',algo = "DQN",save=True,path='./'):
-    ''' 中文画图
-    '''
-    sns.set()
-    plt.figure()
-    plt.title(u"{}环境下{}算法的学习曲线".format(env,algo),fontproperties=chinese_font())
-    plt.xlabel(u'回合数',fontproperties=chinese_font())
-    plt.plot(rewards)
-    plt.plot(ma_rewards)
-    plt.legend((u'奖励',u'滑动平均奖励',),loc="best",prop=chinese_font())
-    if save:
-        plt.savefig(path+f"{tag}_rewards_curve_cn")
-    # plt.show()
+# def plot_rewards(rewards,ma_rewards,tag="train",env='CartPole-v0',algo = "DQN",save=True,path='./'):
+#     sns.set() 
+#     plt.figure() # 创建一个图形实例，方便同时多画几个图
+#     plt.title("average learning curve of {} for {}".format(algo,env))
+#     plt.xlabel('epsiodes')
+#     plt.plot(rewards,label='rewards')
+#     plt.plot(ma_rewards,label='ma rewards')
+#     plt.legend()
+#     if save:
+#         plt.savefig(path+"{}_rewards_curve".format(tag))
+#     plt.show()
 
 def plot_losses(losses,algo = "DQN",save=True,path='./'):
     sns.set()
+    plt.figure()
     plt.title("loss curve of {}".format(algo))
     plt.xlabel('epsiodes')
     plt.plot(losses,label='rewards')