Emma Brunskill

@EmmaBrunskill

Assistant professor, CS, Stanford. Stanford's Human Centered AI (HAI) Institute.

United States
cs.stanford.edu/people/ebrun/
Vrijeme pridruživanja: svibanj 2011.
6 fotografija ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @EmmaBrunskill

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

  1. 24. sij

    Way to get it done! Congratulations to my downstairs academic neighbors, and on their 11 submissions/11 acceptances to ICRA !

    Members of the Interactive Perception and Robot Learning Lab in December 2019
    Proud of my amazing students who worked incredibly hard for this 🙌
    Prikaži ovu nit
    1 reply 42 korisnika označavaju da im se sviđa
    Poništi
  2. proslijedio/la je Tweet
    14. sij

    What will the new age of computer-assisted learning and decision-making look like? expert talks with on The Future of Everything.

    31 proslijeđeni tweet 70 korisnika označava da im se sviđa
    Poništi
  3. 19. pro 2019.

    Thanks for having me!

    . kicking off the afternoon of the Deep RL workshop with RL Challenges Inspired from People-Focused Applications.
    24 korisnika označavaju da im se sviđa
    Poništi
  4. 14. pro 2019.

    Delighted to incoming to ! I’ll be giving talks at Deep RL at 1:30pm West Exhibition Hall C and ML w/Guarantees at 4:45pm West Ballrm B.

    4 proslijeđena tweeta 38 korisnika označava da im se sviđa
    Poništi
  5. proslijedio/la je Tweet
    14. pro 2019.

    With Florian Schaefer Clement Gehring poster 9:30 - 10:30 and 15:20 - 16:20 @ west ballroom A Equality constrained optimization is abundant in reinforcement learning. We solve using competitive gradient descent proposed in main conference

    1 reply 6 proslijeđenih tweetova 27 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  6. 13. pro 2019.

    Curious about the impact of missing features in batch RL for health? Come see Scott Fleming’s poster today at ml4health West Ballrm A 11:30-12:30! jt wk w/Nigam Shah et al.

    22 korisnika označavaju da im se sviđa
    Poništi
  7. 12. pro 2019.

    Today: Counterfactual learning with fairness. Blossom Meteveir presents Offline Contextual Bandits w/ High Probability Fairness Guarantees for a simple tutor, recidivism and loan approval. 5pm-7pm East Exh. Hall BC #113. W/Phil Thomas et al.

    2 proslijeđena tweeta 23 korisnika označavaju da im se sviđa
    Poništi
  8. proslijedio/la je Tweet
    9. pro 2019.

    Machine learning with guarantees. What more could you want?!

    Hey crowd! Fantastic program coming up at the ML w/ Guarantees Workshop on Saturday. Invited talks by , Mohri, Loh, & . Great contributed talks & papers too. It’s all that and a bag of chips!
    1 proslijeđeni tweet 30 korisnika označava da im se sviđa
    Poništi
  9. 10. pro 2019.

    Theory RL fans, Today at NeurIPS Andrea Zanette shows we can fit linear VF to reduce extrapolation errors till 12:45pm [East Exh Hall BC #193], & instance dep bounds for learning MDPs w/a gen model [5:30-7:30 PM @ East Exh Hall BC #178].

    4 proslijeđena tweeta 37 korisnika označava da im se sviđa
    Poništi
  10. proslijedio/la je Tweet
    22. stu 2019.

    It's taken a "village", and over two years of work, but we've finally pushed through to share transparent details about how well models work, and the relationship to "ML fairness" criteria.

    45 proslijeđenih tweetova 131 korisnik označava da mu se sviđa
    Poništi
  11. 22. stu 2019.

    :)

    I’m always happy of seeing AI papers at places like Science because it means AI is becoming mainstream science. I’m even happier when the authors are friends. But I got say, the coolest thing here, by far, is seeing a reference to Hari Seldon & Foundation!
    1 proslijeđeni tweet 27 korisnika označava da im se sviđa
    Poništi
  12. 22. stu 2019.

    Thank you!

    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!
    4 korisnika označavaju da im se sviđa
    Poništi
  13. 21. stu 2019.

    Thanks Wired for covering our work!

    Examples of AI systems behaving badly abound. But a new framework for building AI programs suggests a way to prevent aberrant behavior in machine learning by specifying guardrails in the code from the outset.
    27 korisnika označava da im se sviđa
    Poništi
  14. 21. stu 2019.

    Our paper is "Preventing undesirable behavior of intelligent machines" is available now at:

    1 reply 4 proslijeđena tweeta 30 korisnika označava da im se sviđa
    Poništi
  15. 21. stu 2019.

    Delighted to share our Science article on making it easier ensure AI systems satisfy societal values. Lead by former postdoc Phil Thomas, w/Castro da Silvam, Barto, Giguere, Brun.

    33 proslijeđena tweeta 148 korisnika označava da im se sviđa
    Poništi
  16. 8. stu 2019.

    Encouraging recent empirical work suggests using the stationary Markov distrib to improve the accuracy of off-policy policy estimation in RL. Our theoretical analysis provides conditions for when this may (and may not) improve MSE, as well as assurances that asympt. this helps!

    Happy to share what , myself and have been working on over the last year: "Understanding the Curse of Horizon in Off-Policy Evaluation via Conditional Importance Sampling"
    Prikaži ovu nit
    10 proslijeđenih tweetova 59 korisnika označava da im se sviđa
    Poništi
  17. 5. stu 2019.

    Creating high quality training curriculum is expensive but what if we could use what workers are already doing to provide training to future workers? We find curating past workers' reviews can help future workers write better reviews. Next: let's use ML to automatically curate!

    Was great to present our work on training crowdworkers to do complex tasks by presenting them with peer examples at :
    7 proslijeđenih tweetova 28 korisnika označava da im se sviđa
    Poništi
  18. proslijedio/la je Tweet
    14. lis 2019.

    The Nobel Prize for economics has been awarded to scholars at MIT and Harvard who "introduced a new approach to obtaining reliable answers about the best ways to fight global poverty." MIT's Esther Duflo is only the second woman to win the prize.

    5 replies 174 proslijeđena tweeta 525 korisnika označava da im se sviđa
    Poništi
  19. 9. lis 2019.

    Thank you ! For those interested, our CS234 reinforcement learning lecture notes and assignments are also available here:

    The Reinforcement Learning course (CS234) by is pure gold. It's awesome that it is online.
    62 proslijeđena tweeta 258 korisnika označava da im se sviđa
    Poništi
  20. 23. ruj 2019.

    Congrats to Dr. Christoph Dann for his terrific thesis on advancing accountable, efficient RL! Thanks to his great committee Remi Munos, , Ben Van Roy & Barnabas Poczos. Cake pic is from Chris's policy certificate work [blog post, Fig 2]

    1 reply 1 proslijeđeni tweet 39 korisnika označava da im se sviđa
    Poništi

@EmmaBrunskill 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:

    ·