ddpg求解env_part

DDPG_solver/main.py

@@ -9,7 +9,7 @@ import torch
 import sys
 import os
 sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-from env import PartitionMazeEnv
+from env_partion import PartitionEnv
 # fmt: on
 
 '''Hyperparameter Setting'''
@@ -54,16 +54,16 @@ print(opt)
 
 
 def main():
-    EnvName = ['PartitionMaze_DDPG', 'Pendulum-v1', 'LunarLanderContinuous-v2', 'Humanoid-v4',
+    EnvName = ['Partition_DDPG', 'Pendulum-v1', 'LunarLanderContinuous-v2', 'Humanoid-v4',
                'HalfCheetah-v4', 'BipedalWalker-v3', 'BipedalWalkerHardcore-v3']
-    BrifEnvName = ['PM_DDPG', 'PV1', 'LLdV2',
+    BrifEnvName = ['Part_DDPG', 'PV1', 'LLdV2',
                    'Humanv4', 'HCv4', 'BWv3', 'BWHv3']
 
     # Build Env
     # env = gym.make(EnvName[opt.EnvIdex], render_mode = "human" if opt.render else None)
-    env = PartitionMazeEnv()
+    env = PartitionEnv()
     # eval_env = gym.make(EnvName[opt.EnvIdex])
-    eval_env = PartitionMazeEnv()
+    eval_env = PartitionEnv()
     opt.state_dim = env.observation_space.shape[0]
     opt.action_dim = env.action_space.shape[0]
     # remark: action space【-max,max】

env_partion.py

@@ -18,11 +18,11 @@ class PartitionEnv(gym.Env):
         ##############################
         # 可能需要手动修改的超参数
         ##############################
-        self.params = 'params3'
-        self.CUT_NUM = 2
-        self.ROW_CUT_LIMIT = 1
+        self.params = 'params2'
+        self.CUT_NUM = 4
+        self.ROW_CUT_LIMIT = 3
         self.COL_CUT_LIMIT = 1
-        self.BASE_LINE = 5000
+        self.BASE_LINE = 10000
         self.mTSP_STEPS = 10000
 
         # 车队参数设置
@@ -176,6 +176,7 @@ class PartitionEnv(gym.Env):
                 # print(best_path)
 
                 reward += self.BASE_LINE - best_time
+                print(reward)
 
                 return state, reward, True, False, best_path