rockt - Network

RT @FeryalMP@twitter.comOur paper has been covered by @newscientist@twitter.com! Here is a link to the paper in case you missed it :) paper:...

RT @FeryalMP@twitter.com

Our paper has been covered by @newscientist@twitter.com!
Here is a link to the paper in case you missed it :)
paper: https://arxiv.org/abs/2301.07608
microsite: https://sites.google.com/corp/view/adaptive-agent/ https://twitter.com/newscientist/status/1620366556260704257

🐦🔗: https://twitter.com/FeryalMP/status/1620395385469693953

Article about AdA (https://arxiv.org/abs/2301.07608) in the @NewScientist@twitter.com.RT @newscientist@twitter.comAn artificial intelligence...

Article about AdA (https://arxiv.org/abs/2301.07608) in the @NewScientist@twitter.com.

RT @newscientist@twitter.com

An artificial intelligence has mastered novel tasks it hasn’t been trained on as fast as a group of humans, which could be a step towards generally intelligent AIs https://www.newscientist.com/article/2357017-deepmind-ai-is-as-fast-as-humans-at-solving-previously-unseen-tasks/?utm_medium=social&utm_campaign=echobox&utm_source=Twitter#Echobox=1675159708-1

🐦🔗: https://twitter.com/newscientist/status/1620366556260704257

Imputing data is difficult, not just for AI. This is a terrestrial globe from around 1640 by Jacob Aertsz Colom (you can find it in...

Imputing data is difficult, not just for AI. This is a terrestrial globe from around 1640 by Jacob Aertsz Colom (you can find it in @NMMGreenwich@twitter.com). California is drawn as an island.

RT @_andreilupu@twitter.comAccess to diverse partners is crucial when training robust cooperators or evaluating ad-hoc coordination. In our...

RT @_andreilupu@twitter.com

Access to diverse partners is crucial when training robust cooperators or evaluating ad-hoc coordination. In our top 25% #iclr2023 paper, we tackle the challenge of generating diverse cooperative policies and expose the issue of "sabotages" affecting simpler methods.

A 🧵!

🐦🔗: https://twitter.com/_andreilupu/status/1618667577005441024

RT @verena_rieser@twitter.com"34% of mothers and 12% of fathers globally leave full-time STEMM employment after becoming parents"...

RT @verena_rieser@twitter.com

"34% of mothers and 12% of fathers globally leave full-time STEMM employment after becoming parents" (Sugrue et al., unpublished) https://twitter.com/mothersinsci/status/1618322944056254480

🐦🔗: https://twitter.com/verena_rieser/status/1618515798225735681

RT @zhengyaojiang@twitter.comTrajectory autoencoding planner (TAP) has been accepted by ICLR2023, and the arxiv paper is also updated🥳TAP...

RT @zhengyaojiang@twitter.com

Trajectory autoencoding planner (TAP) has been accepted by ICLR2023, and the arxiv paper is also updated🥳

TAP models the offline RL trajectories with a VQ-VAE and planning is reinterpreted as looking for optimal latent codes.

Highlighted updates and thoughts in 🧵1/N https://twitter.com/zhengyaojiang/status/1562078710265794560

🐦🔗: https://twitter.com/zhengyaojiang/status/1618272741131706368

Great article about our work on AdA and @danijarh@twitter.com's DreamerV3. Scale is coming for...

Great article about our work on AdA and @danijarh@twitter.com's DreamerV3. Scale is coming for RL!

https://www.lesswrong.com/posts/4xGAmZ9GTGAkszHoH/parameter-scaling-comes-for-rl-maybe

RT @FeryalMP@twitter.com

I’m super excited to share our work on AdA: An Adaptive Agent capable of hypothesis-driven exploration which solves challenging unseen tasks with just a handful of experience, at a similar timescale to humans.

https://sites.google.com/corp/view/adaptive-agent/

See the thread for more details 👇 [1/N]

🐦🔗: https://twitter.com/FeryalMP/status/1616035293064462338

RT @savvyRL@twitter.comNow that we can write Tiny Papers @iclr_conf@twitter.com, what should we write about? I'd like to invite all...

RT @savvyRL@twitter.com

Now that we can write Tiny Papers @iclr_conf@twitter.com, what should we write about?

I'd like to invite all established researchers to contribute Tiny Ideas as inspirations, seeds for discussions & future collaborations! #TinyIdeasForTinyPapers

I'll start. Note: bad ideas == good starts.

🐦🔗: https://twitter.com/savvyRL/status/1617974811875217411

RT @j_foerst@twitter.comSince it's impossible to search for past tweets and it's that time of the year again - here is our brief...

RT @j_foerst@twitter.com

Since it's impossible to search for past tweets and it's that time of the year again - here is our brief "How to ML Paper" guide again: https://docs.google.com/document/d/16R1E2ExKUCP5SlXWHr-KzbVDx9DBUclra-EbU8IB-iE/edit#heading=h.16t67gkeu9dx

Good luck with #ICML2023 and remember there is always another deadline!

🐦🔗: https://twitter.com/j_foerst/status/1617670799552569345

RT @savvyRL@twitter.com"Tiny Papers, a DEI initiative"https://iclr.cc/Conferences/2023/CallForTinyPapersSubmit a 2-page paper to...

RT @savvyRL@twitter.com

"Tiny Papers, a DEI initiative"
https://iclr.cc/Conferences/2023/CallForTinyPapers

Submit a 2-page paper to ICLR!

🐦🔗: https://twitter.com/savvyRL/status/1617606473324060673