Diego Gomez @Sisyfuzz

AI researcher @rlai_lab Edmonton, Alberta Joined November 2018

Tweets

103
Followers

57
Following

545
Likes

1K

Marlos C. Machado @MarlosCMachado

11 months ago

The recording of the talk I gave at the @CIFAR_News DLRL Summer School this year at @VectorInst in Toronto is now publicly available: I discussed the interaction between RL and games (with many historical notes). RL and Games: youtube.com/watch?v=lwT05l…

0 6 35 3K 19

Marlos C. Machado @MarlosCMachado

11 months ago

For those interested, the keynotes of the @RL_Conference 2024 are now available online: youtube.com/@RL-conference… Unfortunately, Doina Precup's talk was not recorded, but we have: Andy Barto, @EmmaBrunskill, @FinaleDoshi, @svlevine, David Silver, and @PeterStone_TX.

1 62 250 18K 132

Marlos C. Machado @MarlosCMachado

a year ago

Now that @RL_Conference is over (and what a success it was!), it's time to start thinking about the next one. If you haven't heard yet, RLC is going north. We'll be organizing RLC'25 in Edmonton! I'm very excited about that and look forward to seeing everyone there.

6 27 201 15K 10

Download Image

Dylan Foster 🐢 @canondetortugas

a year ago

Now that I have started using twitter somewhat regularly, let me take a minute to advertise the RL theory lecture notes I have been developing with Sasha Rakhlin: arxiv.org/abs/2312.16730

5 88 632 61K 439

Download Image

Michael Levin @drmichaellevin

a year ago

Final version is out, on the topic of mechanisms by which small cognitive subunits can scale up into larger collective intelligences: "Stress sharing as cognitive glue for collective intelligences: A computational model of stress as a coordinator for morphogenesis"…

18 82 381 24K 167

Finding The Frame Workshop @RLFrameWorkshop

a year ago

🚨@RL_Conference's Finding the Frame Workshop submission deadline is coming up on May 15! 🚨 Help us re-think the conceptual foundations of RL, that often go unchallenged. Tell us how YOU think problems should be framed. Create the next paradigm shift✨🚀 sites.google.com/view/findingth…

1 7 17 8K 4

Marlos C. Machado @MarlosCMachado

2 years ago

Now, as an Assistant Professor, I'll be growing my group more at the University of Alberta. I'll continue to focus on ML and, specifically, reinforcement learning. I'll be hiring PhD and thesis-based MSc students. I'm also hiring a postdoc now. See post: webdocs.cs.ualberta.ca/~machado/postd…

3 16 87 12K 6

Download Image

Jaime Cascante Vega @JaimeCascante09

4 years ago

Echenle la leidita. Con @msantosvega llevamos echándole cabeza desde que nos conocemos a esto y @samueltorresfv nos ayudó a hacerlo realidad en medio de la pandemia.

Royal Society Publishing @RSocPublishing

4 years ago

Echenle la leidita. Con @msantosvega llevamos echándole cabeza desde que nos conocemos a esto y @samueltorresfv nos ayudó a hacerlo realidad en medio de la pandemia.

0 2 3 0 1

Download Image

0 2 10 0 0

Connected Papers @ConnectedPapers

5 years ago

After a long beta, we are launching! Connected Papers is a unique, visual tool to help researchers and applied scientists find and explore papers relevant to their field of work. connectedpapers.com

21 333 726 0 144

Benjamin Heinzerling @benbenhh

6 years ago

BERT is very good at being right for the wrong reasons. Great analysis of BERT's ability to learn exploiting annotation artifacts better than other models: arxiv.org/abs/1907.07355 Performance drops from 77% to random chance level when these artifacts are removed.

0 98 381 0 51

simine vazire @siminevazire

6 years ago

How would I know if my own research area was this wrong? Our usual safeguards won’t save us: peer review, meta-analysis, 100s of conceptual replications, listening to eminent researchers. All failed. This should be keeping us up at night. slatestarcodex.com/2019/05/07/5-h…