bacow/easy-rl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update rainbowdqn

Browse Source
This commit is contained in:
johnjim0816
2022-05-31 01:20:58 +08:00
parent cfc0f6492e
commit c7c94468c9
149 changed files with 1866 additions and 1549 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
codes/common/model.py
View File

@@ -32,10 +32,10 @@ class MLP(nn.Module):
return self.fc3(x)
class Critic(nn.Module):
def __init__(self, n_obs, action_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 + action_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, action_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, action_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, state_dim, action_dim, hidden_dim=256):
def __init__(self, n_states, n_actions, hidden_dim=256):
super(ActorCritic, self).__init__()
self.critic = nn.Sequential(
nn.Linear(state_dim, hidden_dim),
nn.Linear(n_states, hidden_dim),
nn.ReLU(),
nn.Linear(hidden_dim, 1)
)
self.actor = nn.Sequential(
nn.Linear(state_dim, hidden_dim),
nn.Linear(n_states, hidden_dim),
nn.ReLU(),
nn.Linear(hidden_dim, action_dim),
nn.Linear(hidden_dim, n_actions),
nn.Softmax(dim=1),
)

10
codes/common/utils.py
View File

@@ -5,7 +5,7 @@ Author: John
Email: johnjim0816@gmail.com
Date: 2021-03-12 16:02:24
LastEditor: John
LastEditTime: 2021-11-30 18:39:19
LastEditTime: 2022-02-28 11:50:11
Discription:
Environment:
'''
@@ -68,7 +68,13 @@ def plot_losses(losses, algo="DQN", save=True, path='./'):
plt.savefig(path+"losses_curve")
plt.show()
def save_results_1(dic, tag='train', path='./results'):
''' 保存奖励
'''
for key,value in dic.items():
np.save(path+'{}_{}.npy'.format(tag,key),value)
print('Results saved！')
def save_results(rewards, ma_rewards, tag='train', path='./results'):
''' 保存奖励
'''