|
Steven Hansen
@
Zergylord
London, England
|
|
Research Scientist at DeepMind. Slowly learning to learn fast. All opinions my own?
|
|
|
1,110
Tweets
|
417
Following
|
1,389
Followers
|
| Tweets |
|
Steven Hansen
@Zergylord
|
Jan 30 |
|
There is so much potential here:
That feeling when you've been in the saddle for too long.
Drinking the BLEUs away.
Something something Lasso regression...
Hell, "Long short-term memories" is even a good album title. twitter.com/mark_riedl/sta…
|
||
|
|
||
|
Steven Hansen
@Zergylord
|
Jan 30 |
|
I agree, not a replacement -- but they do compete for computing resources.
And generally I've found that it's easier to overfit to a single task than it is to be misled by too few seeds.
Both are problematic, but without infinite compute hard decisions must be made.
|
||
|
|
||
|
Steven Hansen
@Zergylord
|
Jan 30 |
|
Fair point, but it's worth noting that there is a trade-off between # seeds, # baselines, and # and complexity of environment(s).
Personally, I'd prefer a method /w 3 seeds eval'd on 57 tasks with 5 baselines to one with 10 seeds eval'd on 1 task with 2 baselines. twitter.com/pyoudeyer/stat…
|
||
|
|
||
|
Steven Hansen
@Zergylord
|
Jan 10 |
|
Twitter. twitter.com/ComradeLuanne/…
|
||
|
|
||
|
Steven Hansen
@Zergylord
|
Dec 30 |
|
100% agree. Felt guilty contributing to it, but justified it by reassuring myself that having too much pent-up snark is unhealthy.
P.S. Wish you were still at DeepMind so I could get "top-class trolling" on my next performance review ;)
|
||
|
|
||
|
Steven Hansen
@Zergylord
|
Dec 30 |
|
But how else will we ever find out who wins science?!?
;)
|
||
|
|
||
|
Steven Hansen
@Zergylord
|
Dec 30 |
|
Definitely don't wanna be lumped into the "DL solves all" crowd. Wanted to emphasize that fixing the flaws in a system is rarely an armchair exercise in integrating it with the previous system.
But saying so doesn't imply the current system is perfect.
|
||
|
|
||
|
Steven Hansen
@Zergylord
|
Dec 30 |
|
NeurIPS 2019 lives on in all of our hearts!
... And in the Twitter bio of the forgetful
|
||
|
|
||
|
Steven Hansen
@Zergylord
|
Dec 29 |
|
Aristotelian physics may be flawed, but it has been unfairly discarded in favor of Newtonian physics, despite the latter not solving all of the open problems in the field. Clearly the way forward is a hybrid system, wherein aether obeys the conservation of momentum. #AIDebate pic.twitter.com/ZgNpoaqTi7
|
||
|
|
||
|
Steven Hansen
@Zergylord
|
Dec 27 |
|
Episodic coverage-based exploration is a great idea, and this instantiation of it yields great results on hard exploration Atari games.
Great work from my colleagues at #DeepMind twitter.com/bodonoghue85/s…
|
||
|
|
||
| Steven Hansen retweeted | ||
|
Will Dabney
@wwdabney
|
Dec 21 |
|
Happy to have worked with @Zergylord on research combining behavioural mutual information and successor features, which has been accepted for oral presentation at ICLR.
Favorite part: clean answer to where to get the “features” for successor features.
openreview.net/forum?id=BJeAH…
|
||
|
|
||
|
Steven Hansen
@Zergylord
|
Dec 20 |
|
Thanks :)
|
||
|
|
||
|
Steven Hansen
@Zergylord
|
Dec 19 |
|
Conference-decision-anticipation at an all time high.
@iclr_conf I need that sweet sweet email notification! pic.twitter.com/UKQuvXLjWQ
|
||
|
|
||
|
Steven Hansen
@Zergylord
|
Dec 18 |
|
It's fitting that Martin is located at the barycenter of academia :)
|
||
|
|
||
|
Steven Hansen
@Zergylord
|
Dec 16 |
|
I know people who think the original meme was "all your Bayes are belong to us". Can't tell if that makes them more or less nerdy 🤔 twitter.com/economeager/st…
|
||
|
|
||
|
Steven Hansen
@Zergylord
|
Dec 13 |
|
@SchmidhuberAI talk at #NeurIPS2019
I managed to ask a question afterwards:
Q: Did you ever implement, or even attempt to implement, the "special case" where adversarial training is used to mimic a training dataset
A: No.
Hopefully this helps clear up some misconceptions ;) pic.twitter.com/4ofX86rm1n
|
||
|
|
||
| Steven Hansen retweeted | ||
|
Greg Brockman
@gdb
|
Dec 13 |
|
We just released our scientific analysis of OpenAI Five: twitter.com/OpenAI/status/…
We are already using findings from Five in other systems at OpenAI like Dactyl (openai.com/blog/solving-r…) or our multi-agent work (openai.com/blog/emergent-…).
Hope that others find the results useful!
|
||
|
|
||
|
Steven Hansen
@Zergylord
|
Dec 13 |
|
@OpenAI finally released a paper on their DOTA AI. I've given them a lot of crap over the years for not sharing details in a timely manner (and I still stand by most of it that), but this sort of openness is still greatly appreciated.
cdn.openai.com/dota-2.pdf pic.twitter.com/UPzBVCj7RE
|
||
|
|
||
| Steven Hansen retweeted | ||
|
Meire Fortunato
@FortunatoMeire
|
Dec 12 |
|
Very proud of this work. I am not at NeurIPS this year, but my awesome co-authors Melissa Tan, @zergylord and @BlundellCharles are presenting the poster (#192). 🙃🙂🙃 twitter.com/DeepMind/statu…
|
||
|
|
||
|
Steven Hansen
@Zergylord
|
Dec 12 |
|
Very proud to be a part of this! The docker release makes installing and using these environment painless.
Test it out for yourself and come yell at me if something goes wrong ;) twitter.com/DeepMind/statu…
|
||
|
|
||