Alexandre L.-Piché

@A_LPiche

PhD candidate at . Prev. Research intern at and . Interested in RL, probabilistic inference and AI safety. Opinions my own.

Montreal, Qc
Vrijeme pridruživanja: listopad 2011.

Tweetovi

Blokirali ste korisnika/cu @A_LPiche

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

  1. 29. sij

    5th: has been as careless with my bags as with their customers' data , no wonder they fell to 55th (out of 65) “best” airlines. 6/n

    Prikaži ovu nit
    Poništi
  2. 29. sij

    4th: Another representative told me they never scanned my bag and had no idea where it was, in direct conflict with the previous information I was given 5/n

    Prikaži ovu nit
    Poništi
  3. 29. sij

    3rd: The representative told me to call again the next day since I only entered the “very useful visual information about the bags 24h prior” (although I filled this out at the airport when I arrive, over 24h earlier); still telling me that a picture of the bags was useless? 4/n

    Prikaži ovu nit
    Poništi
  4. 29. sij

    2nd: Another representative told me they last scanned my bag at 17:36 (flight took off at 17:45) and he would send a note to LHR and to call me the next day 3/n

    Prikaži ovu nit
    Poništi
  5. 29. sij

    1st interaction: the representative rudely screamed at my gf when she said her phone number (I gave hers as I only had UK#). He then told us that we should enter the visual information of the bag only, saying a picture would be “useless” (??) 2/n

    Prikaži ovu nit
    Poništi
  6. 29. sij

    I wish I had the confidence of h_Airways. They lost my baggage on flight BA95, and now are gaslighting me about it. 1/n

    Prikaži ovu nit
    Poništi
  7. proslijedio/la je Tweet
    26. pro 2019.

    Bayesian methods are *especially* compelling for deep neural networks. The key distinguishing property of a Bayesian approach is marginalization instead of optimization, not the prior, or Bayes rule. This difference will be greatest for underspecified models like DNNs. 1/18

    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet
    21. pro 2019.

    Our submission to was accepted as a spotlight, in it we try to clear up some confusion about Bayesian inference in RL, read it if you want to understand how Bayes and Bellman can get along!

    Poništi
  9. proslijedio/la je Tweet
    14. pro 2019.

    Come see our poster at the Deep RL Workshop... Bring your questions! West Exhibition Hall C

    Prikaži ovu nit
    Poništi
  10. 14. pro 2019.

    Link to the poster

    Prikaži ovu nit
    Poništi
  11. 14. pro 2019.

    Joe Marino is discussing the connections between EM and RL at the DeepRL workshop. A collaboration between and supervised by

    Prikaži ovu nit
    Poništi
  12. proslijedio/la je Tweet
    11. pro 2019.

    The admission period to apply at is closing on December 15. I'm looking for curiosity-driven candidates at all levels and backgrounds to work on understanding and building new reinforcement learning methods.

    Poništi
  13. proslijedio/la je Tweet
    7. pro 2019.

    I am looking for Masters and Ph.D. students to start in Fall 2020. If you are interested in working with me at (), the deadline is Dec 15. More info here: . You can also come to talk to me at .

    Poništi
  14. proslijedio/la je Tweet
    13. stu 2019.

    Very proud to officially join as a Faculty member!

    Poništi
  15. proslijedio/la je Tweet
    10. srp 2019.

    Ready for our workshop on Modeling Inductive Bias in RL! Join us for great talks and panel discussion with Anne Collins (), Todd Gureckis (), Anna Harutyunyan (), and Marlos Machado (@cholodovskis)

    Poništi
  16. proslijedio/la je Tweet
    8. svi 2019.

    Attention , our researchers are presenting their paper, that proposes a formulation of planning as a probabilistic inference problem over future optimal trajectories. 📍 Poster 7 @ 11 AM. , , Cyril Ibrahim, Yoshua Bengio, and .

    Poništi
  17. proslijedio/la je Tweet

    Help the planet by uploading your pictures of flooded houses or buildings, for our Climate Change AI project!

    Poništi
  18. proslijedio/la je Tweet
    16. tra 2019.

    Congratulations are in order for our scientist 👏👏 In addition to defending her at Cambridge, Karolina has been selected for membership at , one of the world’s foremost institutions, for the 2019-2020 program in .

    Poništi
  19. proslijedio/la je Tweet
    3. tra 2019.

    The AI community's trying to do its part! Call for papers for the workshop ->

    Poništi
  20. proslijedio/la je Tweet
    13. velj 2019.

    Working at the intersection of data mining and graph representation learning (e.g., node embeddings or graph neural networks)? Consider submitting to the 2019 SDM workshop on "Deep Learning for Graphs" (deadline March 15)!

    Poništi

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:

    ·