GAN (image generation), DRL (model-free). GAN and DRL are bi-level optimization problems.
-
SIAT(中科院深圳先进院)
- China - Shen Zhen 深圳
- https://www.zhihu.com/people/ceng-yi-yan-8
Block or Report
Block or report Yonv1943
Report abuse
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abusePinned
-
Massively Parallel Deep Reinforcement Learning.
🔥 -
AI4Finance-Foundation/FinRL Public template
FinRL: Financial Reinforcement Learning.
🔥 -
-
Unsupervised-Segmentation Public
A high performance impermentation of Unsupervised Image Segmentation by Backpropagation - Asako Kanezaki
201 contributions in the last year
Less
More
Contribution activity
June 2023
Created 6 commits in 1 repository
Created a pull request in AI4Finance-Foundation/ElegantRL_Solver that received 1 comment
Update H2O_MISO.py
#118
我们曾经在上面的帖子讨论过:
对于解 theta 的不同特征,共用了一样的 LSTM模型参数 ... ... 如果想要推广 'Learn to optimize' 到其他问题,那么就需要把 theta的特征维度从 batch size 维度移动到 inp_dim 或者 out_dim 上
+5
−2
•
1
comment
Opened 3 other pull requests in 1 repository
AI4Finance-Foundation/ElegantRL_Solver
3
merged
Created an issue in AI4Finance-Foundation/ElegantRL_Solver that received 1 comment
📝 update GraphMaxCutEnv to VecEnv
import torch as th
import numpy as np
from torch import Tensor class GraphMaxCutEnv: def __init__(self, num_envs=8, device=th.device('cpu')): txt_p…
1
comment





