David Filliat

@drFilliat

Professor & INRIA FLOWERS team. Robotics, computer vision, machine learning

Vrijeme pridruživanja: rujan 2017.

Tweetovi

Blokirali ste korisnika/cu @drFilliat

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

  1. proslijedio/la je Tweet
    31. sij

    Dear RL Twitter, we are having a discussion with the Stable Baselines maintainers about its future, and we need your opinion. As a big change is required anyway, what framework would you prefer to be the base for V3.0 ?

    Poništi
  2. proslijedio/la je Tweet
    23. sij

    🔴🧠🤖 Our WS Brain-inspired perception, interaction & learning has been accepted for Want to participate? 👉Call for short papers >

    Poništi
  3. proslijedio/la je Tweet
    16. sij

    Our review paper on Explainable Artificial Intelligence has been published in the Elsevier Information Fusion Journal! et al. Check out the 50 days open access article:

    Poništi
  4. proslijedio/la je Tweet
    14. sij

    Our review paper on Continual Learning for Robotics has finally been published in the Elsevier Information Fusion Journal! 🎉 Check out the 50 days open access article at the link below! 👇

    Poništi
  5. proslijedio/la je Tweet
    12. sij
    Poništi
  6. proslijedio/la je Tweet
    9. sij

    Several postdoc and research engineer positions are opened to join my lab Send me an email or DM if you are interested to know more details

    Poništi
  7. 9. sij
    Poništi
  8. proslijedio/la je Tweet
    20. pro 2019.

    Stable Baselines v2.9.0 "Christmas" release is out! We improved plenty of things for the user: - reproducible results (cpu) - multiprocessing helper / automatic wrap - evaluation helper - OpenAI Gym env checker - improved documentation (e.g. c++ export)

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

    We are presenting our work "DisCoRL: Continual Reinforcement Learning via Policy Distillation" at the Deep Reinforcement Learning workshop today with T Sun, G Cai, and A "CL for RL" method applicable on real robots!

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

    Our paper "Continual Learning for Robotics: Definition, Framework, Learning Strategies, Opportunities and Challenges" w , , D Maltoni, A Stoian and has been accepted to "Information Fusion" journal, What a journey ! :D

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

    If you are interested in the regularization methods limitations for continual learning, have a look at our new paper: "Regularization Shortcomings for Continual Learning" w A. Stoian and

    Poništi
  12. proslijedio/la je Tweet
    11. pro 2019.

    We have just added "RL tips and tricks" to the documentation, it covers: - general advice about RL (where to start, which algorithm to choose, rl best practices, …), - tips when creating a custom environment - how to have a working RL implementation

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

    Regularization Shortcomings for Continual Learning. (arXiv:1912.03049v1 [cs.LG])

    Poništi
  14. proslijedio/la je Tweet

    I'll be presenting our paper "Symmetry-Based Disentangled Representation Learning requires Interaction with Environments" at Tuesday evening poster session at (poster #64) Paper: Project page: 1/n

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

    I am at for the week in . If you want to meet and discuss just send me a PM :)

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

    We just updated our article "Continual Learning for Robotics: Definition, Framework, Learning Strategies, Opportunities, and Challenges" w A Stoian and D Maltoni. A survey about and robotics.

    Poništi
  17. proslijedio/la je Tweet

    Retrouvez La Jaune et la Rouge du mois de décembre, avec son dossier spécial sur la et l', coordonné par .

    Poništi
  18. proslijedio/la je Tweet
    20. stu 2019.

    "Continual_Learning_Data_Former" have been updated. A data loader especially conceived for continual learning with now working with !

    Poništi
  19. proslijedio/la je Tweet
    19. stu 2019.

    "Task Label and Continual learning, what is going on? " If you wonder what is a task label in and its different use cases, I just proposed a blog post to make it more clear and disentangle the different settings

    Poništi
  20. proslijedio/la je Tweet

    Une petite vidéo sur les deepfakes avec ! C'était marrant à faire, enjoy :)

    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:

    ·