Berkeley AI Research

@berkeley_ai

We're graduate students, postdocs, faculty and scientists at the cutting edge of artificial intelligence research. (Photo credit: Tony Webster.)

Vrijeme pridruživanja: srpanj 2017.

Tweetovi

Blokirali ste korisnika/cu @berkeley_ai

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

  1. 28. sij

    Early Bird ticket sales for Sessions: Robotics+AI at end on January 31st--buy yours today before prices go up! Student tickets--$50; early bird tickets--$275 + 15% discount with promo code BAIR

    Poništi
  2. proslijedio/la je Tweet
    16. sij

    We just published a blog about our experiences developing with BAIR researchers for scaling up their research -- try it out yourself!

    Poništi
  3. proslijedio/la je Tweet
    15. sij

    "I keep telling my students: you don’t have to fit into a box that someone else made for you, you can make your own box, and you don’t have to fit into that either." I LOVED interviewing amazing prof Gireeja Ranade!

    Poništi
  4. 18. sij

    Check out this awesome project that BAIR student Greg Kahn () worked on at on training an autonomous deep neural network pilot to film while avoiding obstacles!

    Poništi
  5. proslijedio/la je Tweet
    23. pro 2019.

    Check out Glen's post "Emergent Behavior by Minimizing Chaos": Minimizing surprise can lead to complex behaviors that maintain homeostasis, like playing vizDoom, balancing, or learning to play tetris, all w/o any reward. Paper:

    Poništi
  6. 26. pro 2019.

    People give massive amounts of personal data to companies every day. Compensating users for their personal data requires an approach to assigning value to it. Ruoxi Jia's BAIR blog post presents a possible solution--a new method for data valuation.

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

    Laura & Marvin’s blog post on this work is now out:

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

    Model-Based Reinforcement Learning: Theory and Practice New blog post by about the taxonomy of model-based RL methods, when we should use models, and the state-of-the-art MBPO algorithm for sample-efficient RL.

    Poništi
  9. proslijedio/la je Tweet
    25. stu 2019.

    New BAIR blog post on RoboNet! A dataset of multi-robot interactions that we hope will make pretraining the norm, and training your robot from scratch a thing of the past.

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

    My first attempt at a talk for a public audience, explaining some of the intricacies of human-robot coordination. Also a non-technical overview of work with , Jaime Fisac, , and collaborators from Claire Tomlin's group:

    Poništi
  11. proslijedio/la je Tweet
    4. stu 2019.

    Can we learn the language of proteins? Check out our blog post where we discuss Sesame Street, protein plagiarism, and manage to fit in some machine learning along the way.

    Poništi
  12. proslijedio/la je Tweet
    31. lis 2019.

    Model-based RL in space of entities; entities processed w/ locally scoped functions & inferred from raw images through dynamic interaction without supervision on objects w/ J. Tenenbaum

    Poništi
  13. 29. lis 2019.

    How can computers learn to follow instructions from a small amount of language data? Check out this BAIR blog post by David Gaddy on data-efficient language learning by pre-forming representations of an environment!

    Poništi
  14. proslijedio/la je Tweet
    22. lis 2019.

    Computer algorithm developed by UCSF & UC Berkeley scientists bested 2 out of 4 expert radiologists finding tiny brain hemorrhages in head scans — an advance that one day may help doctors treat patients with traumatic brain injuries, strokes & aneurysms.

    Poništi
  15. proslijedio/la je Tweet
    21. lis 2019.

    Excited to share our work: collaboration requires understanding! In Overcooked, self-play doesn't gel with humans: it expects them to play like itself. (1/4) Demo: Blog: Paper: Code:

    Prikaži ovu nit
    Poništi
  16. proslijedio/la je Tweet
    16. lis 2019.

    Excited to be a part of Workshop on Theory of : Where Next. Video of my talk on "Overcoming Mode Collapse and the Curse of Dimensionality" is now available at and the slides are available at .

    Prikaži ovu nit
    Poništi
  17. 15. lis 2019.

    New BAIR blog by Eric Liang, Richard Liaw & Clement Gehring describing a functional API for implementing reinforcement learning algorithms with simplicity in mind!

    Poništi
  18. proslijedio/la je Tweet
    11. lis 2019.
    Poništi
  19. proslijedio/la je Tweet

    Our weekly CompNeuro journal club is back up and running for the quarter. Today, we discussed Cheung et al’s preprint "Superposition of many models into one" from and . Led by AJ Kruse and Satpreet Singh.

    Poništi
  20. proslijedio/la je Tweet
    30. ruj 2019.

    Check out Anusha Nagabandi's blog post about our latest work on dexterous manipulation with model-based RL!

    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:

    ·