chenxiaodong
/
building-agents
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

nothing

This commit is contained in:
chenxiaodong 2024-06-20 09:00:38 +08:00
parent 94d1f3c11c
commit b5a1842147
3 changed files with 2 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
PPO.py
View File

@ -241,7 +241,7 @@ class Arguments:
self.num_threads = 32 # cpu_num for evaluate model, torch.set_num_threads(self.num_threads) self.num_threads = 32 # cpu_num for evaluate model, torch.set_num_threads(self.num_threads)
'''Arguments for training''' '''Arguments for training'''
self.num_episode = 2000 # to control the train episodes for PPO self.num_episode = 1000 # to control the train episodes for PPO
self.gamma = 0.995 # discount factor of future rewards self.gamma = 0.995 # discount factor of future rewards
self.learning_rate = 2 ** -14 # 2e-4 self.learning_rate = 2 ** -14 # 2e-4
self.soft_update_tau = 2 ** -8 # 2 ** -8 ~= 5e-3 self.soft_update_tau = 2 ** -8 # 2 ** -8 ~= 5e-3

1
module.py
View File

@ -126,7 +126,6 @@ class Wind:
self.power_coefficient * self.generator_efficiency) / 1e3 self.power_coefficient * self.generator_efficiency) / 1e3
else: else:
self.current_power = 0 self.current_power = 0
return self.current_power return self.current_power
def gen_cost(self, current_power): def gen_cost(self, current_power):

2
tools.py
View File

@ -129,7 +129,7 @@ class Arguments:
self.num_threads = 32 # cpu_num for evaluate model, torch.set_num_threads(self.num_threads) self.num_threads = 32 # cpu_num for evaluate model, torch.set_num_threads(self.num_threads)
'''Arguments for training''' '''Arguments for training'''
self.num_episode = 2000 self.num_episode = 1000
self.gamma = 0.995 # discount factor of future rewards self.gamma = 0.995 # discount factor of future rewards
# self.reward_scale = 1 # an approximate target reward usually be closed to 256 # self.reward_scale = 1 # an approximate target reward usually be closed to 256
self.learning_rate = 2 ** -14 # 2 ** -14 ~= 6e-5 self.learning_rate = 2 ** -14 # 2 ** -14 ~= 6e-5