update

codes/PPO/task0.py

@@ -20,7 +20,7 @@ class PPOConfig:
         self.continuous = False # 环境是否为连续动作
         self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")  # 检测GPU
         self.train_eps = 200 # 训练的回合数
-        self.eval_eps = 20 # 测试的回合数
+        self.test_eps = 20 # 测试的回合数
         self.batch_size = 5
         self.gamma=0.99
         self.n_epochs = 4

codes/PPO/task1.py

@@ -20,7 +20,7 @@ class PPOConfig:
         self.continuous = True # 环境是否为连续动作
         self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")  # 检测GPU
         self.train_eps = 200 # 训练的回合数
-        self.eval_eps = 20 # 测试的回合数
+        self.test_eps = 20 # 测试的回合数
         self.batch_size = 5
         self.gamma=0.99
         self.n_epochs = 4

codes/PPO/train.ipynb

@@ -68,7 +68,7 @@
     "        self.result_path = curr_path+\"/results/\" +self.env+'/'+curr_time+'/results/'  # path to save results\n",
     "        self.model_path = curr_path+\"/results/\" +self.env+'/'+curr_time+'/models/'  # path to save models\n",
     "        self.train_eps = 200 # max training episodes\n",
-    "        self.eval_eps = 50\n",
+    "        self.test_eps = 50\n",
     "        self.batch_size = 5\n",
     "        self.gamma=0.99\n",
     "        self.n_epochs = 4\n",
@@ -144,7 +144,7 @@
     "    print(f'Env:{cfg.env}, Algorithm:{cfg.algo}, Device:{cfg.device}')\n",
     "    rewards= []\n",
     "    ma_rewards = [] # moving average rewards\n",
-    "    for i_ep in range(cfg.eval_eps):\n",
+    "    for i_ep in range(cfg.test_eps):\n",
     "        state = env.reset()\n",
     "        done = False\n",
     "        ep_reward = 0\n",

codes/PPO/train.py

@@ -32,7 +32,7 @@ def eval(cfg,env,agent):
     print(f'环境：{cfg.env_name}, 算法：{cfg.algo}, 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.eval_eps):
+    for i_ep in range(cfg.test_eps):
         state = env.reset()
         done = False
         ep_reward = 0
@@ -47,7 +47,7 @@ def eval(cfg,env,agent):
                 0.9*ma_rewards[-1]+0.1*ep_reward)
         else:
             ma_rewards.append(ep_reward)
-        print('回合：{}/{}, 奖励：{}'.format(i_ep+1, cfg.eval_eps, ep_reward))
+        print('回合：{}/{}, 奖励：{}'.format(i_ep+1, cfg.test_eps, ep_reward))
     print('完成训练！')
     return rewards,ma_rewards
 
@@ -74,7 +74,7 @@ if __name__ == '__main__':
             self.continuous = False # 环境是否为连续动作
             self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")  # 检测GPU
             self.train_eps = 200 # 训练的回合数
-            self.eval_eps = 20 # 测试的回合数
+            self.test_eps = 20 # 测试的回合数
             self.batch_size = 5
             self.gamma=0.99
             self.n_epochs = 4