09 2022 档案
摘要：错误： RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [100, 1]], w
阅读全文
摘要：改进 Gt = Gt - mean(Gt) 代码 model.py import torch import torch.nn as nn import torch.nn.functional as F class Model(nn.Module): def __init__(self): super
阅读全文
摘要：策略梯度，入门样例 原文链接： https://www.cnblogs.com/Twobox/ 参考链接： https://datawhalechina.github.io/easy-rl/#/chapter4/chapter4 https://zhuanlan.zhihu.com/p/358700
阅读全文
