Open kilitougo opened 4 years ago
Did you try Torch or TF implementation? , i've been trying Torch implementation for two weeks and i've got multiple errors. I was making simples changes in this code, and i'm still getting some mismatch size errors.
I tried torch implementation and made some changes too. I only tried RDM module because according to the paper RDM module should yield the highest accuracy.
Hey, guys, have you notice the cost function (y_i - a_i)^2 in page 5 of the paper? As far as I know, if the authors are using DQN algorithm, the a_i should be replaced by action-value function Q(h_i, a, theta). In my understand, the a_i is the action value, so I am confused why they use (y_i-a_i)^2 as cost function.
Hi, I am interested in your research and ran the RDM model which should have the highest accuracy according to your paper. However, the accuracy I got is only around 80 percent. I made some minor changes to your code because it is not runnable. Could you show me how to get the accuracy in the paper? Thank you very much.
请问您介不介意分享一下代码,我不知道如何修改可以运行起来
Hi, I am interested in your research and ran the RDM model which should have the highest accuracy according to your paper. However, the accuracy I got is only around 80 percent. I made some minor changes to your code because it is not runnable. Could you show me how to get the accuracy in the paper? Thank you very much.
Hello, can you tell me how to modify it? The error keeps appearing. Thanks a lot!
你好,我对你的研究对象,并运行了 RDM 模型,根据你的论文,该模型应该具有最高的准确度。不过,我得到的准确率只有 80% 左右。我对你的代码一些小改动,因为它不可运行。你能告诉我如何获得论文的准确性吗?非常感谢你。
你好,能告诉我怎么修改吗?错误不断出现。非常感谢!
您好,代码后来跑通了吗?跑通的话能告诉我怎么修改代码吗?
Hi, I am interested in your research and ran the RDM model which should have the highest accuracy according to your paper. However, the accuracy I got is only around 80 percent. I made some minor changes to your code because it is not runnable. Could you show me how to get the accuracy in the paper? Thank you very much.