search

dgriff777 / a3c_continuous

A continuous action space version of A3C LSTM in pytorch plus A3G design
Apache License 2.0
258 stars 59 forks source link

learn from 2D pixel array / conv2D #3

Closed dusty-nv closed 6 years ago

dusty-nv commented 6 years ago

Hi @dgriff777 , thanks for your repo. Was wondering if you might be able/interested to add a 2D convolution model (i.e. using Conv2D as opposed to Conv1D like is in A3C_CONV today) to learn from pixel array as opposed to learn from 1D parameters? Thanks!

dgriff777 commented 6 years ago

Hi @dusty-nv, so attached my other repo below with Conv2D example. Hope that helps :)

https://github.com/dgriff777/rl_a3c_pytorch

dusty-nv commented 6 years ago

Thank you! I will look into it.

-------- Original message -------- From: David Griffis notifications@github.com Date: 5/16/18 7:00 PM (GMT-05:00) To: dgriff777/a3c_continuous a3c_continuous@noreply.github.com Cc: Dustin Franklin dustinf@nvidia.com, Mention mention@noreply.github.com Subject: Re: [dgriff777/a3c_continuous] learn from 2D pixel array / conv2D (#3)

Hi @dusty-nvhttps://github.com/dusty-nv, so attached my other repo below with Conv2D example. Hope that helps :)

https://github.com/dgriff777/rl_a3c_pytorch

- You are receiving this because you were mentioned. Reply to this email directly, view it on GitHubhttps://github.com/dgriff777/a3c_continuous/issues/3#issuecomment-389692383, or mute the threadhttps://github.com/notifications/unsubscribe-auth/AOpDKz9ecsdSIf5lMXvmF0neZ4yy0fb4ks5tzK-CgaJpZM4UBUaM.

This email message is for the sole use of the intended recipient(s) and may contain confidential information. Any unauthorized review, use, disclosure or distribution is prohibited. If you are not the intended recipient, please contact the sender by reply email and destroy all copies of the original message.