schaul.bsky.social
RL researcher at DeepMind
https://schaul.site44.com/ 🇱🇺
25 posts
3,116 followers
278 following
Regular Contributor
Conversation Starter
comment in response to
post
The RL team is a small team led by David Silver. We build RL algorithms and solve ambitious research challenges. As one of DeepMind's oldest teams, it has been instrumental in building DQN, AlphaGo, Rainbow, AlphaZero, MuZero, AlphaStar, AlphaProof, Gemini, etc. Help us build the next big thing!
comment in response to
post
The sound of two users joining per second: "tik", "tok"...
comment in response to
post
Dynamic programming has a fun origin story. In 1950, Bellman wanted to coin a term that "was something not even a Congressman could object to".
See here:
pubsonline.informs.org/doi/pdf/10.1...
comment in response to
post
Ohh... good morning to you too!
Clearly this got off on the wrong foot: do you want to try again, maybe more constructively (in the spirit of bluesky not being the other place)? This is a preprint, so I'd be happy to hear your suggestions for making it less "ignorant"...
comment in response to
post
Either one or many players. For "improvement" to be well-defined, one agent must be special (see footnote 6), but the multi-agent setting has many benefits.
comment in response to
post
1: open-ended means that it will keep producing novel and learnable artifacts (see the definition here: arxiv.org/abs/2406.04268), on the timescale of interest for the observer.
2: I think as a thought experiment it is valid, as it could work in principle, but of course it hasn't been built?
comment in response to
post
In section 5 (second paragraph), there's about a dozen references to language games people are already using (one per paper), some with ingenious ways to provide feedback.
Also, I suspect the workshop will ultimately have the poster abstracts online with plenty of additional material!
comment in response to
post
I'll also be giving a talk about this at the @neuripsconf.bsky.social workshop on "Language Gamification" in two weeks. Pop by if you're around!
language-gamification.github.io
comment in response to
post
@colah.bsky.social: with a few years' hindsight, how do you see the Distill space now? Is there a chance for a reboot or a rebirth in another form?
comment in response to
post
I think the Distill journal was really valuable in this space, but unfortunately is no longer around to help...
distill.pub
comment in response to
post
If you're happy with a book-length answer (to the broader question on which technologies empower whom, why, and when), Acemoglu and Johnson have some excellent analysis:
shapingwork.mit.edu/power-and-pr...
comment in response to
post
Oh, this is my tribe!
Some other people here that I appreciate for their infectious positivity:
@akoopa.bsky.social
@jhamrick.bsky.social
@rockt.ai
@pcastr.bsky.social
@luisazintgraf.bsky.social
@dabelcs.bsky.social
@aditimavalankar.bsky.social
comment in response to
post
Ok, we'll have to make sure a restricted the closed system generates an open-ended set of ideas then! 😉
comment in response to
post
Now if only that pack could keep growing in, say, an open-ended way...
comment in response to
post
@togelius.bsky.social often has out-of-distribution takes -- but be warned, some of his thoughts come in book-length: mitpress.mit.edu/978026254934...
comment in response to
post
Done, twice: I think the board is not the only viable recipient...