Clarification of some abbreviations?

[mingyr]

Dear Deepminder:

During a group meeting I was raised a question about the meanings of abbreviations in the demo code of TRFL when I tried to introduce TRFL to my lab members. So I have to ask it here.

It reads:

q_tm1: the action value in the source state of a transition.
a_tm1: the action that was selected in the source state.

What does m1 mean here? I know "q" stands for action value, "t" stands for time step, I tried to figure "m1" stands for what, but it is not so intuitive.

Could you please help me on that? Thanks a lot.

[mingyr]

BTW, I thought 'm1' might be 'minus 1', but I am not quite sure. I would like to hear the original naming convention from you. Thanks.

[miljanm]

Hi, that's right, m1 stands for minus 1, i.e. at the previous timestep.

…

On Sat, 17 Nov 2018 at 04:52, Yurui MING ***@***.***> wrote: BTW, I thought 'm1' might be 'minus 1', but I am not quite sure. I would like to hear the original naming convention from you. Thanks. — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub <#7 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/ABeeDV53Yeg3uvmD0_goIjsbRSqRKL2Wks5uv5YCgaJpZM4YnRkv> .

[mingyr]

Got it, thanks a lot. An adorable naming convention, haha.