Kevin Waugh (@kdub0) profile picture

Research Scientist at @SonyAI_global

Alberta, Canada
Joined March 2009
Photo by Kevin Waugh (@kdub0)Photo by Kevin Waugh (@kdub0)
Kevin Waugh retweeted
The really cool part of REBEL is how it generalizes the classic Natural Policy Gradient algorithm (my favorite RL alg) while being as scalable as REINFORCE :) Some details:
In the words of Billy Idol, give a "rebel yell" for REBEL: a strikingly simple RL algorithm (it's just regression! no clipping / critics!) that scales to generative models (both LLMs and Diffusion Models!) and has deep theoretical interpretations: arxiv.org/abs/2404.16767. [1/8]
1
7
34
9,481
Kevin Waugh retweeted
We are looking for brilliant and creative candidates with strong programming skills to join us at the Discovery team at @GoogleDeepMind 🧙 We build AI agents that discover new knowledge using RL, planning and LLMs. DM me if you have specific questions about working with us 🙏
5
31
4
282
52,534
I’ve been a bit quiet for the past year! It's because I’ve been building 🤫 I'm excited to share that the Artificial.Agency team is coming out of stealth with a sneak peek. More to come. Keep your eyes peeled 👀 – at San Francisco, CA
Artificial.Agency is building the behavior engine driving the future of interactive digital entertainment. We are co-creating the next level of gaming with our studio partners and you’re invited to be part of the journey. Join our pilot. artificial.agency/
2
5
40
3,097
Kevin Waugh retweeted
As our work in Game AI expands, so does our team. Sony AI is now hiring for a Reinforcement Learning Research Intern to join our global Game AI group. Join us in leveraging AI to develop new, enriching gaming experiences. ow.ly/e7BI50Q6aek
10
1
68
11,529
Kevin Waugh retweeted
RL PhD students: Want to work on hard RL problems with applications to modern video games? Apply for an internship position at Sony AI! #ReinforcementLearning #AI ai.sony/joinus/job-roles/Rei…
2
13
71
8,259
Kevin Waugh retweeted
I'm super excited to share AlphaZeroᵈᵇ, a team of diverse #AlphaZero agents that collaborate to solve #Chess puzzles and demonstrate increased creativity. Check out our paper to learn more! arxiv.org/abs/2308.09175 A quick 🧵(1/n)
4
64
10
325
94,612
DeepMind Alberta is hiring research scientists this year. Come join us in understanding and creating interactive, playful AI. deepmind.com/careers/jobs/88…
6
65
6
398
The @DeepMind Alberta team, led by @RichardSSutton, @PatrickPilarski and myself, is hiring Research Scientists and a Research Engineer. deepmind.com/careers/jobs/88… deepmind.com/careers/jobs/37…
2
20
4
75
Stats and summaries from the #NeurIPS2020 reviewing process, including answers to important q's: 'Were the desk-rejects accurate?' and 'What area has the best acceptance rate?' bit.ly/37hj9aP
11
93
20
332
Kevin Waugh retweeted
Great work by my colleagues at @DeepMind_Health showing a great application of ML models to early detection/prediction of Acute Kidney Injury (AKI), giving the chance to intervene earlier.
Kidney injury occurs in 1 of 5 hospitalized patients. A deep learning #AI algorithm can predict 1-2 days before it strikes @Nature by @weballergy @joe_ledsam @mustafasuleymn @DeepMind_Health nature.com/articles/s41586-0… My editorial nature.com/articles/d41586-0… @NatureNV
1
80
4
285
Grats @marcgbellemare on the most starred github project of the year! octoverse.github.com/project…
1
3
Well-deserved front cover of Science for the DeepStack team! nitter.gq/DeepStackAI/status/860…
The DeepStack paper was just published in the print edition of Science, and we made the front cover! science.sciencemag.org/conte…
3
1
16
Kevin Waugh retweeted
TBT to when kick drums were a bit on the flabby side 😂 youtube.com/watch?v=OaWKmFnD… @anjunabeats #trancefamily #FakeAwake
1
2
6
Kevin Waugh retweeted
To celebrate 10,000+ users we're giving away 2% of @Max_Silver s WSOP Main Event action to one lucky person who follow us and RT #giveaway
2
218
7
252
E_TOO_MUCH caffeine. *twitch*
1
Kevin Waugh retweeted
Google, don't turn off Reader. Signed, The Internet vrge.co/16sZmy6
32
1,239
123
I can't type very fast on my $300 ergonomic keyboard #FirstWorldProblems
1
Britain has stringent anti-gun laws, and they're still under the control of the monarchy. #NRATips
5
3
Took extra care to find a table away from any babies and two mothers come sit next to me #FirstWorldProblems
1