init of neural network

[KK666-AI]

Dear Author,

Thanks for sharing the excellent work on reproducing reinforcement learning algorithms. I notice that you use init_ = lambda m: init(m, nn.init.orthogonal_, lambda x: nn.init.constant_(x, 0)) to initialize neural networks and I find it makes neural networks much more stable. However, I don't understand the underlying theory of this trick, could you have an explanation or give some related papers?

Thanks.

[realiti4]

Hi, I've also realized, if I don't use this init method, a2c doesn't improve when number of processes are not high enough, and I'm also curious about the reason behind it. I'd also be happy to learn more about this, if someone can explain, thank you.

[KarlXing]

Looking forward to an explanation too!

[shtse8]

I am looking forward to an explanation as well!