Marc G. Bellemare

@marcgbellemare

Reinforcement learning, information theory, generally competent AI. Opinions my own.

Montréal, Canada
marcgbellemare.info
Vrijeme pridruživanja: travanj 2011.
14 fotografija ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @marcgbellemare

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @marcgbellemare

  1. Prikvačeni tweet
    22. ožu 2019.

    New post looking back at RL research at Google Brain in Montreal over the last ~18 months: One more year and we'll know why distributional RL works? @cholodovskis

    68 proslijeđenih tweetova 331 korisnik označava da mu se sviđa
    Poništi
  2. 15. sij

    Beyond thrilled to see this analysis by colleagues Will Dabney, Zeb Kurth-Nelson, Matt Botvinick and colleagues in Nature: Evidence that the brain encodes distributional reward predictions (in the distributional RL sense). Congrats!

    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/
    Prikaži ovu nit
    8 proslijeđenih tweetova 46 korisnika označava da im se sviđa
    Poništi
  3. 13. sij

    The lives of so many, tangled up in arbitrariness. My heart goes out to friends, peers, and academic colleagues, near and far, who lost someone in the tragedy of . We are all connected.

    7 proslijeđenih tweetova 84 korisnika označavaju da im se sviđa
    Poništi
  4. proslijedio/la je Tweet
    6. sij

    The FATE group at MSR Montréal has multiple internship positions open for summer 2020. If you are interested in studying the societal implications of artificial intelligence, we are seeking interns who can complement the existing skills on the team.

    42 proslijeđena tweeta 74 korisnika označavaju da im se sviđa
    Poništi
  5. proslijedio/la je Tweet
    6. sij

    Deadline for applications is in 2 days (Jan 8)! Contact myself or if you are interested and have some questions. Note that these are independent positions allowing the fellow to develop their own research vision and academic profile.

    Looking for senior and independent postdocs in comp stats, machine learning, stats methodologies! Check out the research of the group to see if you’d like to joint us :)
    1 reply 12 proslijeđenih tweetova 20 korisnika označava da im se sviđa
    Poništi
  6. 14. pro 2019.

    Don't miss 's spotlight on analyzing sample-based RL algorithms using distributional tools today 11:40 at the OptRL workshop! Work w/ Doina Precup, Prakash Panangaden, & myself

    5 proslijeđenih tweetova 28 korisnika označava da im se sviđa
    Poništi
  7. proslijedio/la je Tweet
    12. pro 2019.

    Anybody at interested in applications of the JKO paper, come check out my poster Stochastically Dominant Distributional RL, at the Safety and Robustness in Decisin Making workshop.

    0:05
    Oldies but goldies: Jordan, Kinderlehrer, Otto, The Variational Formulation of the Fokker-Planck Equation. Showed that heat equation is Optimal Transport flow (i.e. flow of particles) minimizing Shannon entropy. Other entropies lead to non-linear PDEs.
    2 proslijeđena tweeta 18 korisnika označava da im se sviđa
    Poništi
  8. proslijedio/la je Tweet
    12. pro 2019.

    Looking forward for workshops tomorrow - my favorite part of . and I will speak about the MEMENTO observation in Atari agents tomorrow at 4:15 in the BARL workshop. Come see us at the poster! , , yoshuawonttweet,

    Korisnici , , i
    20 proslijeđenih tweetova 74 korisnika označavaju da im se sviđa
    Poništi
  9. 11. pro 2019.

    A rare opportunity to see a party chair in their natural environment! A short cab ride away from the convention centre, too.

    🎵hey friends in vancouver🎵 if you want to see some LIVE JAZZ while here, i'll be doing a show at (1608 Commercial Drive) on wednesday, 9:30-11:30pm. geordie hart on bass🎸, josh payne on drums🥁, and me on keys🎹. maybe some winds. come by!
    3 proslijeđena tweeta 23 korisnika označavaju da im se sviđa
    Poništi
  10. proslijedio/la je Tweet
    8. pro 2019.

    Congratulations to our colleague Lin Xiao for the test of time award!!! Online convex optimization and mirror descent for the win!! (As always? :-).)

    1 reply 49 proslijeđenih tweetova 257 korisnika označava da im se sviđa
    Poništi
  11. proslijedio/la je Tweet
    6. pro 2019.

    1 machine learning faculty position at & at assistant or associate level; Jan 6th deadline. Come join the deep learning and reinforcement learning mecca! Catch us at . See

    21 proslijeđeni tweet 37 korisnika označava da im se sviđa
    Poništi
  12. proslijedio/la je Tweet
    5. pro 2019.

    . is just around the corner! The banquet on Saturday will have 🎶AWESOME LIVE MUSIC!!🎶 Thrilled to announce the lineup of performers, along with a brief description of the selection process. Songs will be a surprise Sat. night 🕵🏾‍♂️

    11 proslijeđenih tweetova 63 korisnika označavaju da im se sviđa
    Poništi
  13. 3. pro 2019.

    This is a great extension of Coin Run, really curious to see what research it will inspire!

    0:29
    We're releasing Procgen Benchmark, 16 procedurally-generated environments for measuring how quickly a reinforcement learning agent learns generalizable skills. This has become the standard research platform used by the OpenAI RL team:
    7 proslijeđenih tweetova 39 korisnika označava da im se sviđa
    Poništi
  14. proslijedio/la je Tweet
    27. stu 2019.

    If you are interested in graduate studies on reinforcement learning, consider applying to the Department of Computer Science, University of Toronto and work with me.

    7 replies 71 proslijeđeni tweet 205 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  15. proslijedio/la je Tweet
    25. stu 2019.

    psc trio! this friday nov. 29th, 9pm! see you there!

    1 proslijeđeni tweet 9 korisnika označava da im se sviđa
    Poništi
  16. proslijedio/la je Tweet
    24. stu 2019.

    Come spend 18 months with us in Montreal! We haven't had many applicants interested in optimization in the past so please apply!

    If you haven't applied yet to the - AI Residency Program, now is a great time apply: Please share and RT
    25 proslijeđenih tweetova 119 korisnika označava da im se sviđa
    Poništi
  17. 22. stu 2019.

    Great work by colleague on deep-learning a particularly important metric for reinforcement learning. With video!

    2:13
    Thrilled to share my paper: "Scalable methods for computing state similarity in deterministic MDPs", which was accepted to Paper: Code: Intro video 👇🏾👇🏾 1/4
    Prikaži ovu nit
    3 proslijeđena tweeta 37 korisnika označava da im se sviđa
    Poništi
  18. 21. stu 2019.

    Looking forward to this!

    Game Night tonight at ! Get your ticket, meet cool peeps, play good games, drink and solve all the world's problems (maybe). Organized by . Tickets here:
    8 korisnika označava da im se sviđa
    Poništi
  19. proslijedio/la je Tweet
    15. stu 2019.

    In case today was too tight (e.g. with the AAMAS deadline) we have given out a few small extensions to our AAAI-RLG workshop, so it's only fair to let everyone know. We will be closing the submission system Monday at noon Edmonton time.

    Excited to share that we are organizing the AAAI Workshop on Reinforcement Learning in Games (AAAI-RLG), to be held February 7th or 8th in New York City! Submissions due November 15th. with Julien Perolat and Marc Lanctot
    4 proslijeđena tweeta 15 korisnika označava da im se sviđa
    Poništi
  20. proslijedio/la je Tweet
    14. stu 2019.

    Slides for my RL lecture Special thanks to Ksenia, and others for contributing much of the content.

    We are about to start 4th day at . We are going to upload the lectures slides to our web as we get them. For now, you can enjoy the ones from on reinforcement learning here:
    34 proslijeđena tweeta 117 korisnika označava da im se sviđa
    Poništi
  21. 11. stu 2019.

    Very excited to see this work presented at AAAI -- congratulations !

    presenting my paper "Scalable methods for computing state similarity in deterministic Markov Decision Processes" in poster session 2 (thursday, noon) this paper just got accepted to 🎉! paper and code coming soon, here's the poster in the meantime:
    Prikaži ovu nit
    4 proslijeđena tweeta 41 korisnik označava da mu se sviđa
    Poništi

@marcgbellemare još nije objavio nijedan Tweet.

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.

    Možda bi vam se svidjelo i ovo:

    ·