Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @FlorinGogianu
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @FlorinGogianu
-
Prikvačeni tweet
So I made it through my first poster session at
#EEML2019, presenting ways of sampling from the replay memory based on the uncertainty of the value function approximator.pic.twitter.com/iX1ZEZ5uFf
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Florin Gogianu proslijedio/la je Tweet
More from our research seminar:
@senya_ashuha talks about current state of uncertainty estimation in Deep Learninghttps://youtu.be/lNIoJmi2tO8Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Florin Gogianu proslijedio/la je Tweet
TCS Twitter, what are your absolute favorite textbooks?
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Another call for the most interesting results in ML in 2019.https://twitter.com/zacharylipton/status/1212421519613349891 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
I highly recommend
@fdabl blog. Several times I found myself revisiting some of the posts knowing I’ll find certain concepts well explained in there.https://twitter.com/fdabl/status/1210546272811307008 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Florin Gogianu proslijedio/la je Tweet
Have you heard of "RL as Inference"? https://arxiv.org/pdf/1805.00909.pdf … ... you might be surprised that this framing completely ignores the role of uncertainty! (confusing, since it talks a lot about "posteriors") Our
#ICLR spotlight tries to make sense of this: https://openreview.net/forum?id=S1xitgHtvS …pic.twitter.com/tOxMnBiRvO
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
I've been wondering the same so I hope this gets many comments.https://twitter.com/jachiam0/status/1207975400929976320 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Florin Gogianu proslijedio/la je Tweet
We're pleased to let you know that your submission, On Bonus Based Exploration Methods In The Arcade Learning Environment, has been accepted at
#ICLR2020! https://openreview.net/forum?id=BJewlyStDr … This huge endeavor was led by@aalitaiga. W/@LiamFedus,@marcgbellemare &@AaronCourville. More
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Florin Gogianu proslijedio/la je Tweet
Our
#GiftAGamer '19 Holiday Contest is live!

How to enter?
1. RT this photo.
2. Say something nice about a fellow gamer (& tag them) in the replies with #GiftAGamer 3. If selected, you + the friend you tagged BOTH win an RTX 2080 Ti! Learn more: https://nvidia.com/en-us/geforce/contests/gift-a-gamer/https://www.nvidia.com/en-us/geforce/news/giftagamer-geforce-rtx-2080-ti-contest-2019/ …pic.twitter.com/kILgn0TlJw
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Florin Gogianu proslijedio/la je Tweet
Very excited about my new paper! https://arxiv.org/abs/1912.02074 We formulate the on-policy max-return RL objective w.r.t *arbitrary* offline data and without *any* explicit importance correction. Amazingly, the gradient of the objective w.r.t pi is exactly the on-policy policy gradient!pic.twitter.com/R3g7tOjxNJ
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Florin Gogianu proslijedio/la je Tweet
I made a flowchart to help people choose which causal inference book to read :)https://bradyneal.com/which-causal-inference-book …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Check-out the work done by my colleagues on
#GraphNeuralNetwork for learning interaction representations in videos.https://twitter.com/DutaIulia/status/1199372700294295552 …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Florin Gogianu proslijedio/la je Tweet
Causality for Machine Learning. (arXiv:1911.10500v1 [cs.LG]) https://ift.tt/2KRSyVO
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Florin Gogianu proslijedio/la je Tweet
Book draft with proofs on RL https://rltheorybook.github.io/
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Florin Gogianu proslijedio/la je Tweet
Improving episodic control w/
@MartaSarrico@KloudStrife Memory-Efficient Episodic Control Reinforcement Learning with Dynamic Online k-means: https://arxiv.org/abs/1911.09560 Sample-Efficient Reinforcement Learning with Maximum Entropy Mellowmax Episodic Control: https://arxiv.org/abs/1911.09615Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Florin Gogianu proslijedio/la je Tweet
Have you, like me, had a vague sense that work was happening to make model uncertainty more calibrated, but not known in more detail where the field was? This paper - which does broad testing of different uncertainty methods - is for you!
#mlwritingmonthhttps://www.shortscience.org/paper?bibtexKey=journals/corr/abs-1906-02530&a=decodyng …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Florin Gogianu proslijedio/la je Tweet
Folks, have a winner. For the stochastic bandit, this gem from Odalric-Ambrym Maillard's thesis, called EwS, works incredibly well and gives explicit probabilities on the arms. I compare EwS with Thompson & Tsallis in https://gist.github.com/n17s/44a7ddcf078a041755a2c537aa9d3e14 …
@djhsu@neu_rips@CsabaSzepesvaripic.twitter.com/0Zzp916JYU
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Florin Gogianu proslijedio/la je Tweet
We are hiring in our approx-Bayes team at RIKEN-AIP. Post-docs (2 positions), RA (4 positions), interns (15 positions). Job posting: https://tinyurl.com/y2zummmy Team page: https://tinyurl.com/y2pa43y8 Email: jobs-abi-riken-aip@googlegroups.com Help me spread the word. Retweets appreciated
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Florin Gogianu proslijedio/la je Tweet
School segregation in Romania. Assigning Roma children to different buildings, scheduling break times at different hours to avoid interaction with white kids. Just in case you thought the recent news cycle about Bulgarian racist laws was isolated.https://www.ziaruldeiasi.ro/stiri/pauze-la-ore-diferite-pentru-ca-elevii-romi-sa-nu-interactioneze-cu-ceilalti-copii--235110.html#.XcEbpWNzqzo.facebook …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Florin Gogianu proslijedio/la je Tweet
Thank you
@federicolois! For those interested, our CS234 reinforcement learning lecture notes and assignments are also available here: http://web.stanford.edu/class/cs234/schedule.html …https://twitter.com/federicolois/status/1181242692019347457 …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Florin Gogianu proslijedio/la je Tweet
Excited to share that I’m teaching a *new course* on multi-task & meta-learning! Topics incl. optimization-based meta-learning, lifelong learning, meta-RL , etc Slides & assignments being posted. Lecture videos to be publicly released after the course. http://cs330.stanford.edu pic.twitter.com/Gmve2kUvHW
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.