Comment by arjun-p on [deleted post] 2024-08-06T19:43:11.501Z

I don't think this will work because we are already using subscripts to denote which environment's list we are referring to

Comment by arjun-p on [deleted post] 2024-07-30T17:28:26.253Z

I'm not. I guess this is the part that makes it confusing

for readability we define $A\left(s\right):=A_{\sigma \left(s\right)}$ and $P_{\sigma \left(s\right)}$ to be the accessible and outer action spaces of $s$ respectively

Do you have a suggestion for alternate notation? I use this because we often need to refer to the action space corresponding to a state. I think this would be needed even with the language framing.

(I also assigned $j:=\sigma \left(s^{\prime }\right)$ to make it more readable)

Comment by arjunpi (arjun-p) on 2023 in AI predictions · 2024-03-14T06:05:51.798Z · LW · GW

Do you have any predictions about the first year when AI assistance will give a 2x/10x/100x factor "productivity boost" to AI research?

Comment by arjunpi (arjun-p) on Open Thread – Winter 2023/2024 · 2024-02-04T18:59:11.297Z · LW · GW

Hey, I've been reading stuff from this community since about 2017. I'm now in the SERI MATS program where I'm working with Vanessa Kosoy. Looking forward to contributing something back after lurking for so long :P