Chelsea Finn

@chelseabfinn

CS Faculty . Research scientist . PhD from , EECS BS from

Palo Alto, CA
Vrijeme pridruživanja: lipanj 2014.

Tweetovi

Blokirali ste korisnika/cu @chelseabfinn

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

  1. Prikvačeni tweet
    25. ruj 2019.

    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.

    Poništi
  2. proslijedio/la je Tweet
    2. velj
    Odgovor korisnicima

    To quote Hamming: "The great scientists often make this error. They fail to continue to plant the little acorns from which the mighty oak trees grow. They try to get the big thing right off."

    Poništi
  3. 22. sij

    Excited to share PCGrad, a super simple & effective method for multi-task learning & multi-task RL: project conflicting gradients On Meta-World MT50, PCGrad can solve *2x* more tasks than prior methods w/ Tianhe Yu, S Kumar, Gupta, ,

    Poništi
  4. 13. sij

    We're organizing a workshop on 'Beyond "Tabula Rasa" in RL' (BeTR RL) at & looking forward to your submissions! Deadline: Feb 10 Invited speakers include , Ishita Dasgupta, Abhishek Gupta, Martha White, with as a panelist.

    Poništi
  5. 2. sij

    Can robots learn about the world by observing humans? Learn to predict with both interaction & observation (of humans), then use the model to accomplish goals.
 w. Schmeckpeper , Xie, , Tian, ,

    Poništi
  6. 19. pro 2019.

    Can we discover structure & meta-learn across it in unsegmented time series data? MOCA simultaneously detects changepoints & meta-learns across time for continuous adaptation Continuous Meta-Learning without Tasks w , Sharma,

    Poništi
  7. 13. pro 2019.

    I'll be discussing this work and other challenges in meta-learning at the Bayesian Deep Learning Workshop at 1:20 pm, West Exhibition Hall C.

    Poništi
  8. 10. pro 2019.

    Interested RL algorithms that learn to follow instructions, use hierarchical abstractions, and achieve compositional generalization? We investigate the many benefits of language in RL. We'll be at poster #197, at 10:45 am! w Murphy

    Poništi
  9. 10. pro 2019.

    Meta-RL relies heavily on manually-defined task distributions. CARML constructs curricula of tasks *without supervision* in the loop of meta-learning. On Weds, Allan Jabri will present a spotlight at 10:30 am in Hall A, poster #53 at 5:30 pm!

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

    Can we distribute meta-RL, with local policy learners distilled into a centralized meta-policy? Find out about guided meta-policy search, which can solve complex meta-RL tasks! Russell Mendonca will present the work at NeurIPS at 4:45 pm in Ballroom A + B, poster #42 at 5:30 pm

    Poništi
  11. 9. pro 2019.

    We're presenting our work on meta-learning with implicit differentiation Come find us at the Tuesday evening poster session #47, tomorrow 5:30-7:30 pm.

    Poništi
  12. 9. pro 2019.

    Meta-learning has a peculiar, widespread problem that leads to terrible performance when faced with seemingly benign changes to the training set-up. We analyze this problem & provide a solution: w/ , , Zhou,

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

    . & I are co-organizing the next Conference Apr 1, 2020—no joke!—on the topic Triangulating Intelligence: Melding Neuroscience, Psychology, and AI. Botvinick——Tenenbaum——save the date!

    Poništi
  14. 25. stu 2019.

    Sudeep Dasari wrote an excellent blog post on our work on RoboNet, cross-posted on the SAIL blog: We imagine a future where robots share data *across* research labs, just like the rest of machine learning.

    Poništi
  15. proslijedio/la je Tweet
    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.

    Poništi
  16. 11. stu 2019.

    I'm on my way to in Montevideo, Uruguay. Looking forward to giving a talk on ML for robots, joining the Women in AI panel, and meeting talented researchers!

    Poništi
  17. 24. lis 2019.

    Tired of your robot learning from scratch? We introduce RoboNet: a dataset that enables fine-tuning to new views, new envs, & entirely new robot platforms. w/ Dasari Tian Bucher Schmeckpeper Singh

    Poništi
  18. 24. lis 2019.

    The Meta-World paper is now out! Includes an eval of 8 methods & 5 eval modes. We look forward to seeing how your new algorithms fare on the suite of 50 tasks.

    Poništi
  19. 19. ruj 2019.

    An accessible blog post and nice visualizations by on our NeurIPS paper on meta-learning with implicit gradients!

    Poništi
  20. 15. ruj 2019.

    New paper: Hierarchical visual foresight learns to generate visual subgoals to break down a goal into smaller pieces. Accomplishes long-horizon vision-based tasks, without *any* supervision. w/ Suraj Nair Paper: Code:

    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:

    ·