Tweets
- Tweets, current page.
- Tweets & replies
- Media
You blocked @wwdabney
Are you sure you want to view these Tweets? Viewing Tweets won't unblock @wwdabney
-
Will Dabney Retweeted
By teaching machines to understand our true desires, one scientist hopes to avoid the potentially disastrous consequences of having them do what we command.https://www.quantamagazine.org/artificial-intelligence-will-do-what-we-ask-thats-a-problem-20200130/ …
Thanks. Twitter will use this to make your timeline better. UndoUndo -
Our paper 'A distributional code for value in dopamine-based reinforcement learning' on the cover of
@nature! Read it here: http://rdcu.be/b0mtA Shout out to the amazing artists/designers at@DeepMind who make this possible, while we get to focus on the research.https://twitter.com/EricTopol/status/1222582512792129536 …
Thanks. Twitter will use this to make your timeline better. UndoUndo -
Will Dabney Retweeted
I haven't found a single person who has used jax and said they don't like it. I've been actively priming people to criticize it, but noone does. Instead they tell me how good it feels getting off of Tensorflow. Looking forward to jaxxing myself soon.
Thanks. Twitter will use this to make your timeline better. UndoUndo -
Will Dabney Retweeted
Hey everyone, I'm so excited to share my recent interview on Music & AI plus "A Geometric Perspective on Reinforcement Learning" with
@samcharrington for the@twimlai podcast. Check it out! https://twimlai.com/talk/339 via@twimlaihttps://twitter.com/twimlai/status/1217908672375992320 …Thanks. Twitter will use this to make your timeline better. UndoUndo -
Will Dabney Retweeted
The reciprocal inspiration of
#AI and neuroscience. A@DeepMindAI@nature paper this week on the mechanism of reinforcement learning https://www.nature.com/articles/s41586-019-1924-6.epdf?author_access_token=ASaTR4qMH190wSHiKLjQ7NRgN0jAjWel9jnR3ZoTv0OgnvLoVhK46-VND2gsGkjz36rZENj3hLKoFtZ6yylssm1cot8UrjoCWaDrIBKZs-uF0doLijXxV5GpU93RmqJeFMCQ_BzuM9Sr7acs_dVtKg%3D%3D … by@wwdabney@zebkDotCom and colleagues with an excellent explainer by@_KarenHao@techreview https://www.technologyreview.com/s/615054/deepmind-ai-reiforcement-learning-reveals-dopamine-neurons-in-brain/ …pic.twitter.com/SdT7Jvh9Zf
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
Thank everyone! You can also read the paper for free here: http://rdcu.be/b0mtA
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
And it all started (for me) almost exactly three years ago working with
@marcgbellemare and Remi on distributional RL: http://proceedings.mlr.press/v70/bellemare17a/bellemare17a.pdf …Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
It has been an incredible collaboration with my co-authors, especially working with
@zebkDotCom and Matt Botvinick. Also incredibly grateful to Naoshige Uchida and Clara Starkweather from Harvard, as well as Remi Munos and Demis Hassabis for their work and constant endurance! 2/Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
When neuroscience and AI researchers get to chatting, cool stuff happens! My first, and I hope not last, trip into neuroscience has been published in Nature. 1/https://twitter.com/DeepMind/status/1217510884085583873 …
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
Almost all of these (IMO) apply equally well to research. I most disagree with the “short 1:1, long group meetings” one, but do other research people think most of these apply to them?https://twitter.com/sama/status/1214274038933020672 …
Thanks. Twitter will use this to make your timeline better. UndoUndo -
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo
-
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 -
So fun how non-stationary our perception is. It’s not hard to get the direction cued onto any physical change. Opening/closing hand, blinking, you can even pretend to spin it this way and that with your thumb and it will switch.https://twitter.com/FelixHill84/status/1203616080415068160 …
Thanks. Twitter will use this to make your timeline better. UndoUndo -
Will Dabney Retweeted
Really excited for
#NeurIPS2019 next week and to present our spotlight on credit assignment :) https://papers.nips.cc/paper/9413-hindsight-credit-assignment … tl;dr We can rewrite value functions in terms of a hindsight quantity that explicitly captures credit assignment and get a whole new family of RL algs!
pic.twitter.com/Hr6vqqaH6Z
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
Let’s just hope Fox News doesn’t run this, or he might just declare war on all our allies.https://twitter.com/ianbremmer/status/1202047174793682944 …
0:24Thanks. Twitter will use this to make your timeline better. UndoUndo -
Wow, Phil Thomas and co-authors invention of Seldonian ML hits on so many levels. I love the clean framing of the problem, the sci-fi callback, and that it actually makes progress in an area where most articles are more philosophical than algorithmic!https://science.sciencemag.org/content/366/6468/999 …
Thanks. Twitter will use this to make your timeline better. UndoUndo -
Will Dabney Retweeted
Shout out to my friend and collaborator Phil Thomas, along with
@EmmaBrunskill and others, for their new paper in Science on a general framework for defining and avoiding undesirable behavior in ML algorithms:https://science.sciencemag.org/content/366/6468/999 …Thanks. Twitter will use this to make your timeline better. UndoUndo -
I found this inspiring. Seeing the leaders in our field leveraging their position to push back on government, not for some new funding but to get deserving researches to a conference. Hoping Canada is proud enough of their AI leadership to fix these visa issues.https://twitter.com/JeffDean/status/1192630774312263680 …
Thanks. Twitter will use this to make your timeline better. UndoUndo -
This is an impressive manipulation task! However, the agent isn’t “learning to solve the Rubik’s cube”. It is using a hard coded algorithm to solve the cube and has been trained to implement the limited set of macro actions needed for that algorithm. Still very cool!https://twitter.com/OpenAI/status/1184135128869527552 …
0:18Thanks. Twitter will use this to make your timeline better. UndoUndo -
London Underground
@TfL, an expensive torturous actual monopoly with 50% downtime. Come rain, or snow, or gentle breeze you can be sure of a train failure to ruin your day.Thanks. 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.