Tweets
- Tweets, current page.
- Tweets & replies
- Media
You blocked @Zergylord
Are you sure you want to view these Tweets? Viewing Tweets won't unblock @Zergylord
-
Pinned Tweet
Excited to announce our work on memory generalization in Deep RL is out now! We created a suite of 13 tasks with variants to test interpolation and extrapolation. Our new MRA agent out-performs baselines, but these tasks remain an open challenge. https://arxiv.org/abs/1910.13406 1/npic.twitter.com/jnnPr5ISk7
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
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.https://twitter.com/mark_riedl/status/1223027372330561536 …
Thanks. Twitter will use this to make your timeline better. UndoUndo -
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.https://twitter.com/pyoudeyer/status/1222911050028285954 …
Thanks. Twitter will use this to make your timeline better. UndoUndo -
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.
#AIDebatepic.twitter.com/ZgNpoaqTi7Thanks. Twitter will use this to make your timeline better. UndoUndo -
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
#DeepMindhttps://twitter.com/bodonoghue85/status/1210557534978953216 …Thanks. Twitter will use this to make your timeline better. UndoUndo -
Steven Hansen Retweeted
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.https://openreview.net/forum?id=BJeAHkrYDS …Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
Conference-decision-anticipation at an all time high.
@iclr_conf I need that sweet sweet email notification!pic.twitter.com/UKQuvXLjWQ
Thanks. Twitter will use this to make your timeline better. UndoUndo -
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
https://twitter.com/economeager/status/1206433176215674881 …Thanks. Twitter will use this to make your timeline better. UndoUndo -
Steven Hansen Retweeted
We just released our scientific analysis of OpenAI Five: https://twitter.com/OpenAI/status/1205541134925099008 … We are already using findings from Five in other systems at OpenAI like Dactyl (https://openai.com/blog/solving-rubiks-cube/ …) or our multi-agent work (https://openai.com/blog/emergent-tool-use/ …). Hope that others find the results useful!
0:11Thanks. Twitter will use this to make your timeline better. UndoUndo -
Steven Hansen Retweeted
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).

https://twitter.com/DeepMind/status/1205084437987438592 …Thanks. Twitter will use this to make your timeline better. UndoUndo -
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 ;)https://twitter.com/DeepMind/status/1205084437987438592 …
Thanks. Twitter will use this to make your timeline better. UndoUndo -
Is it too late to rebrand entropy regularization as "the free-will prior"?
#NeurIPS2019pic.twitter.com/Jwx2yjTe8pThanks. Twitter will use this to make your timeline better. UndoUndo -
"now let's talk about consciousness" Can we not?pic.twitter.com/PZXlHcZbZA
Thanks. Twitter will use this to make your timeline better. UndoUndo -
I like London, but it'll be so nice to just forget about Brexit and think about nothing but AI for a week.
#NeurIPS2019 Day 1:pic.twitter.com/FJfA9ktpqQ
Thanks. Twitter will use this to make your timeline better. UndoUndo -
I'm at
#NeurIPS2019 all week; DMs always open so let me know if any AI Twitter folk wanna chat about intrinsic motivation, generalization in DRL, and/or AI Twitter drama :) And do come by our wonderful poster on Thursday to check out how well memory-based DRL agents generalize!https://twitter.com/Zergylord/status/1189571063606337536 …
Thanks. Twitter will use this to make your timeline better. UndoUndo -
Great tutorial at
@NeurIPSConf Turns out that "dataset shit" is really hard.pic.twitter.com/sGVctScLec
Thanks. Twitter will use this to make your timeline better. UndoUndo -
Lightning in Palo Alto? What a narrative violation.https://twitter.com/fchollet/status/1203483983499018247 …
Thanks. Twitter will use this to make your timeline better. UndoUndo -
Steven Hansen Retweeted
May be I am the only weird one who feels uncomfortable with the idea that one of the pre-readings list includes chapters from three books that are not publicly available as free versions. Perhaps
@GaryMarcus can share those chapters with us? Or is it indirect books marketing?https://twitter.com/GaryMarcus/status/1203340331464327168 …Thanks. Twitter will use this to make your timeline better. UndoUndo -
Unblocked, so ignore that first bit ;) Still curious about the connections between reversible networks and Gary's ideas though!
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
Got blocked by
@GaryMarcus for not sufficiently appreciating my time with his 2001 book, The Algebraic Mind. Re: universally qualified one-to-one mapping, iRevNets satisfy this property, right? Would be curious to know what he has to say on that paper: https://arxiv.org/abs/1802.07088Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.