David-Lee-1990

@zhaoyingjun 连接中的 dgk_shooter_z.conv 下载不动，请问是百度盘上的资料删除了吗

@todpole3 I re-edited my issue to show more detailed information of the training results.

In MINERVA, there is no dropout and I try to add this advancement on it. Follow your idea, I use dropout to encourage diverse sampling and the policy gradient is...

No, i use the original one.

hi, i run a sanity-checking experiments by setting the keep rate in [1.0, 0.99, 0.98, 0.97, 0.95, 0.93, 0.90]. The results of hits@1 on training batch is as follows: **1.0...

> The most noticeable difference is that the dev result you reported without action dropout is close to what we have with 0.1 action dropout and significantly higher than what...

> > I tested this for two versions: one is relation-only and the other not. Both versions show the similar results as i stated in the issue. > > @David-Lee-1990...

> Besides action dropout rate, did you use the same set of hyperparameters as we did in the configuration files? If not, would you mind sharing your set of hyperparameters?...

> And one more question, did you observe similar trend on other datasets using MINERVA code + action dropout? @todpole3 Follow your advice, I test action dropout on nell-995 today,...

Is this problem solved?