pixyzoo icon indicating copy to clipboard operation
pixyzoo copied to clipboard

Published 20 hours ago • verified publisher icon masa-su

Loss

Open BingCS opened this issue 5 years ago • 2 comments

Hi,

Many thanks for your contribution on implementing GQN.

Recently, I implemented GQN. After the training on rooms_ring_camera, I found that the loss will converge to around 6950 after 200K iterations, which means after the sigma decrease to 0.7, the loss will maintain at a stable level. But in their original paper, the final loss is just 6.1. I don’t understand the where is the problem. Do you have the same problem? Many thanks in advance!

Looking forward to your reply!

BingCS avatar Jul 27 '19 22:07 BingCS

I am having the same issue. Is there anyways to improve this?

phongnhhn92 avatar Oct 26 '19 15:10 phongnhhn92

Dear developer, hello. The question I want to ask you is whether DeepMindGQN can be trained on windows? I haven't found a training method, can you share it with me?

male-lion avatar Mar 06 '20 02:03 male-lion