Sarah
@sarahbechtle
Followers
73
Following
37
Media
0
Statuses
19
Joined October 2020
We are excited to announce our @RoboticsSciSys workshop "Risk Aware Decision Making: From Optimal Control to Reinforcement Learning" We will bring together experts from different fields with insights that might shape the future of Risk Aware Robotics.
0
2
9
The video/slides from my talk "Free your Meta-Learning Algorithm" at the @iclr_conf'21 WS on Learning to Learn are publicly viewable (along with the other excellent keynotes). https://t.co/oJV1LZo0MN
0
10
25
The video recording from our learning to learn for robotics workshop at @ieee_ras_icra is now available on YouTube! We hope you'll find it as inspiring and insightful as we did https://t.co/c9WGVQ6s41
1
7
12
Join us on a robotics journey across meta learning land! Our Learning to Learn for Robotics workshop starts in 2hrs! We have a list of exciting speakers who are going to challenge the boundaries of learning to learn for robotics!
1
2
7
Zoom link, talks and agenda can be found on our website: https://t.co/McYwsPROW1 co-organised with @sarahbechtle, @YevgenChebotar, @tmh31 and @_kainoa_
1
1
1
We also extended the deadline :) more info on our website
sites.google.com
The workshop aim is to provide an informative overview of the existing challenges in using meta learning for robotics and set the grounds for future development.
Don't forget to submit your abstracts on Learning-to-Learn to our learning-to-learn ICRA'21 workshop - the robotics edition :)!
0
0
2
This workshop is starting in a few hours. Please excuse my inability to get dates right 😂
At ICLR? Interested in meta-learning? Come check out the WS on Learning to Learn tomorrow (Fri 6 May). I'll be giving a semi-contrarian talk about freeing our meta-learning algorithms from preconceived notions of what meta-learning is or should be. https://t.co/EBSS7yWB8t
0
2
5
Join us at the Learning-to-Learn workshop starting at 7AM PT today! How to join: https://t.co/UaycnNGhWC Invited talks + panel with Jennifer Raymond, @ermgrant , @egrefen, @janexwang , Ishita Dasgupta, Risto Miikkulainen +Poster session!
0
5
14
Remember to submit your abstracts to our learning-to-learn ICRA'21 workshop - the robotics edition More details: https://t.co/eAMp8Pt85d Abstract Deadline: May 15th with @yadrimz @sarahbechtle @YevgenChebotar @tmh31
1
6
18
3/3 papers accepted for #icra2021 with @majid_khadiv, @sarahbechtle, @ludo_righetti @_kainoa_ and Andrea Del Prete ! Here are the links R-AL and ICRA "Impedance Optimization for Uncertain Contact Interactions Through Risk Sensitive Optimal Control" https://t.co/Bo1kWBRdyq
1
1
11
If your revolutionary meta learning idea turned out failing, don't worry! Consider submitting it to our Learning to Learn workshop @iclr_conf. We solicit negative results, we believe this is key to understanding meta learning limitations! We got you 😉🤠👌
Remember to submit your work to our learning-to-learn workshop @iclr_conf ! We specifically also solicit negative results that help us understand the limitations and boundaries of learning-to-learn/meta-learning. More details: https://t.co/MeakeRqQx9 Deadline: Feb 26h
0
5
8
One week left before the submission deadline for our Learning-to-Learn workshop @iclr_conf 2021!! We welcome all thoughts and ideas on meta learning and solicit submissions with negative results! I cannot wait to learn about your work!!
1
4
12
Sarah Bechtle, a #PhD student working with Professor @ludo_righettim, won the best student paper award @icpr2020milan for her work on “Meta-Learning via Learned Loss.” Congratulations, Sarah!
0
5
33
Remember to submit your work to our learning-to-learn workshop @iclr_conf ! We specifically also solicit negative results that help us understand the limitations and boundaries of learning-to-learn/meta-learning. More details: https://t.co/MeakeRqQx9 Deadline: Feb 26h
sites.google.com
LIVE PARTICiPATION
What are the boundaries of Learning-To-Learn, and how can we push them? Our workshop @iclr_conf brings together neuroscience and machine learning experts to discuss these and other meta-learning topics! Burning ideas 💡? Submissions are open! Details: https://t.co/MeakeRqQx9
1
4
5
Want to know how you can teach your robot manipulation skills from visual demonstrations? Check out our blog post to find out! with @_dasneha_ @sarahbechtle @yadrimz @dineshjayaraman and Akshara Rai
How can we teach AI skills using visual demos? We’ve created and open-sourced a new technique that teaches robots to learn a model of their environment, observe human behavior, and develop its own reward system. Learn how we built it: https://t.co/rfge6zaKYt
#machinelearning
1
5
27
What are the boundaries of Learning-To-Learn, and how can we push them? Our workshop @iclr_conf brings together neuroscience and machine learning experts to discuss these and other meta-learning topics! Burning ideas 💡? Submissions are open! Details: https://t.co/MeakeRqQx9
2
14
67
Congratulations to all my collaborators, especially @sarahbechtle, @amolchanov86, @YevgenChebotar , for winning the overall best student paper award @icpr2020milan !! Paper: https://t.co/Orzu9izbPf Code: https://t.co/letYGmxI3D
4
14
53
Excited to present our work on meta learning via learned loss @icpr2020milan - a fully differentiable meta-learning framework for learning parametric loss functions! AND: we open sourced code: https://t.co/BNoOAFnaOM
@amolchanov86 @YevgenChebotar @egrefen @ludo_righetti @_kainoa_
sites.google.com
VIDEO
1
8
19