@ericeaton.bsky.social
Faculty at the University of Pennsylvania. Lifelong machine learning and AI for robotics and precision medicine: continual learning, transfer & multi-task learning, deep RL, multimodal ML, and human-AI collaboration. seas.upenn.edu/~eeaton
Reposted
🎉 Announcing the winners of the #CoLLAs2025 Early-Career Spotlight Program!
These rising stars are pushing the boundaries of lifelong & continual learning, adaptation, and embodied AI.
👇 A thread introducing their work & talks.
#AI #MachineLearning #ContinualLearning #LifelongLearning
These rising stars are pushing the boundaries of lifelong & continual learning, adaptation, and embodied AI.
👇 A thread introducing their work & talks.
#AI #MachineLearning #ContinualLearning #LifelongLearning
August 5, 2025 at 5:17 PM
🎉 Announcing the winners of the #CoLLAs2025 Early-Career Spotlight Program!
These rising stars are pushing the boundaries of lifelong & continual learning, adaptation, and embodied AI.
👇 A thread introducing their work & talks.
#AI #MachineLearning #ContinualLearning #LifelongLearning
These rising stars are pushing the boundaries of lifelong & continual learning, adaptation, and embodied AI.
👇 A thread introducing their work & talks.
#AI #MachineLearning #ContinualLearning #LifelongLearning
It was lots of fun moderating this theatrical, wrestling-themed debate on CS vs AI degrees at the 2025 CRA Summit. Thanks to my panelists for being such good sports and having great insights! #CRASummit
@vasant-h.bsky.social
@vasant-h.bsky.social
July 30, 2025 at 1:43 AM
It was lots of fun moderating this theatrical, wrestling-themed debate on CS vs AI degrees at the 2025 CRA Summit. Thanks to my panelists for being such good sports and having great insights! #CRASummit
@vasant-h.bsky.social
@vasant-h.bsky.social
Reposted
Come say hi at our #ICML poster today during Poster Session 1 (W-600)! Joint work with @ericeaton.bsky.social @marcelhussing.bsky.social @optimistsinc.bsky.social @aaroth.bsky.social @mkearnsphilly.bsky.social!
arxiv.org/abs/2502.11828
arxiv.org/abs/2502.11828
Intersectional Fairness in Reinforcement Learning with Large State and Constraint Spaces
In traditional reinforcement learning (RL), the learner aims to solve a single objective optimization problem: find the policy that maximizes expected reward. However, in many real-world settings, it ...
arxiv.org
July 15, 2025 at 2:38 PM
Come say hi at our #ICML poster today during Poster Session 1 (W-600)! Joint work with @ericeaton.bsky.social @marcelhussing.bsky.social @optimistsinc.bsky.social @aaroth.bsky.social @mkearnsphilly.bsky.social!
arxiv.org/abs/2502.11828
arxiv.org/abs/2502.11828
Reposted
📢 Only 8 weeks to #CoLLAs2025!
Tackle the real-world challenges of ML: catastrophic forgetting, dist. shift, continual RL, lifelong learning & more.
📍 Aug 11–14 @upenn.edu
🧠 Talks, workshops, posters, tutorials & community
🔗 lifelong-ml.cc/Conferences/...
#ContinualLearning #AI #MachineLearning
Tackle the real-world challenges of ML: catastrophic forgetting, dist. shift, continual RL, lifelong learning & more.
📍 Aug 11–14 @upenn.edu
🧠 Talks, workshops, posters, tutorials & community
🔗 lifelong-ml.cc/Conferences/...
#ContinualLearning #AI #MachineLearning
CoLLAs
Collas
lifelong-ml.cc
June 17, 2025 at 1:53 PM
📢 Only 8 weeks to #CoLLAs2025!
Tackle the real-world challenges of ML: catastrophic forgetting, dist. shift, continual RL, lifelong learning & more.
📍 Aug 11–14 @upenn.edu
🧠 Talks, workshops, posters, tutorials & community
🔗 lifelong-ml.cc/Conferences/...
#ContinualLearning #AI #MachineLearning
Tackle the real-world challenges of ML: catastrophic forgetting, dist. shift, continual RL, lifelong learning & more.
📍 Aug 11–14 @upenn.edu
🧠 Talks, workshops, posters, tutorials & community
🔗 lifelong-ml.cc/Conferences/...
#ContinualLearning #AI #MachineLearning
Reposted
I'll be at @iclr-conf.bsky.social next week! Ping me if you want to chat about RL, life, or the universe! I'll be presenting our MAD-TD paper openreview.net/forum?id=6Rt... at the poster session, and I will also most likely be lurking at the Robot Learning workshop.
MAD-TD: Model-Augmented Data stabilizes High Update Ratio RL
Building deep reinforcement learning (RL) agents that find a good policy with few samples has proven notoriously challenging. To achieve sample efficiency, recent work has explored updating neural...
openreview.net
April 17, 2025 at 6:00 PM
I'll be at @iclr-conf.bsky.social next week! Ping me if you want to chat about RL, life, or the universe! I'll be presenting our MAD-TD paper openreview.net/forum?id=6Rt... at the poster session, and I will also most likely be lurking at the Robot Learning workshop.
Reposted
Do you want to get the most out of your samples, but increasing the update steps just destabilizes RL training? Our #ICLR2025 spotlight 🎉 paper shows that using the values of unseen actions causes instability in continuous state-action domains and how to combat this problem with learned models!
February 11, 2025 at 10:14 PM
Do you want to get the most out of your samples, but increasing the update steps just destabilizes RL training? Our #ICLR2025 spotlight 🎉 paper shows that using the values of unseen actions causes instability in continuous state-action domains and how to combat this problem with learned models!
Reposting a postdoc opportunity in field robotics at Penn, in case anyone missed it the first time around.
We're hiring a postdoc in field robotics at the University of Pennsylvania's GRASP lab, which will focus on multi-robot autonomy, control/coordination, and perception for the DARPA Triage Challenge. #robotics
For details and to apply, see www.seas.upenn.edu/~eeaton/open...
For details and to apply, see www.seas.upenn.edu/~eeaton/open...
Open Research Positions
www.seas.upenn.edu
December 23, 2024 at 5:15 AM
Reposting a postdoc opportunity in field robotics at Penn, in case anyone missed it the first time around.
This is so sad. It’s also yet another reason why I strongly believe that hardware shouldn’t be completely dependent on cloud services. It’s fine as a value-added on top of local functionality, but loss of the cloud service, or even the internet, should never brick a device.
An AI company that made a robot called Moxie to socialize children with special needs went under and so now parents have to explain to their kids that their robots are dying. For @aftermath.site aftermath.site/moxie-robot-...
AI Company That Made Robots For Kids Goes Under, Robots Die - Aftermath
Embodied, maker of the AI robot called Moxie, is shuttering. With their closing, parents have to explain to their kids that Moxie is dead.
aftermath.site
December 15, 2024 at 3:57 AM
This is so sad. It’s also yet another reason why I strongly believe that hardware shouldn’t be completely dependent on cloud services. It’s fine as a value-added on top of local functionality, but loss of the cloud service, or even the internet, should never brick a device.
Reposted
Been seeing a lot of RL architectures use layer norms as "design choice" without elaborating why it's needed. If you are curious take a look at our paper: arxiv.org/abs/2403.05996 TLDR: Layer norms stop your critic from diverging early on and stabilize training. cc @cvoelcker.bsky.social
Dissecting Deep RL with High Update Ratios: Combatting Value Divergence
We show that deep reinforcement learning algorithms can retain their ability to learn without resetting network parameters in settings where the number of gradient updates greatly exceeds the number o...
arxiv.org
December 3, 2024 at 3:01 PM
Been seeing a lot of RL architectures use layer norms as "design choice" without elaborating why it's needed. If you are curious take a look at our paper: arxiv.org/abs/2403.05996 TLDR: Layer norms stop your critic from diverging early on and stabilize training. cc @cvoelcker.bsky.social
A starter pack of researchers in AI and ML at Penn, currently woefully incomplete. Please PM to be added or suggest names.
go.bsky.app/5SxWsoZ
go.bsky.app/5SxWsoZ
December 3, 2024 at 4:50 AM
A starter pack of researchers in AI and ML at Penn, currently woefully incomplete. Please PM to be added or suggest names.
go.bsky.app/5SxWsoZ
go.bsky.app/5SxWsoZ
New feed on continual learning, lifelong learning, and related ML topics: bsky.app/profile/did:...
I hope you find it useful. Please let me know if you notice it is missing any posts, so that I can adjust the regular expression.
I hope you find it useful. Please let me know if you notice it is missing any posts, so that I can adjust the regular expression.
November 28, 2024 at 4:29 PM
New feed on continual learning, lifelong learning, and related ML topics: bsky.app/profile/did:...
I hope you find it useful. Please let me know if you notice it is missing any posts, so that I can adjust the regular expression.
I hope you find it useful. Please let me know if you notice it is missing any posts, so that I can adjust the regular expression.
Come join us in Philadelphia in August for CoLLAs 2025!
We've had three successful editions since 2021, with our fourth edition announced just recently!
Follow @collasconf.bsky.social for updates and join the conversation! 🚀
A couple of organizers are also attending NeurIPS 2024 so if you are around, come say hi 👋 3/3
Follow @collasconf.bsky.social for updates and join the conversation! 🚀
A couple of organizers are also attending NeurIPS 2024 so if you are around, come say hi 👋 3/3
November 28, 2024 at 4:14 PM
Come join us in Philadelphia in August for CoLLAs 2025!
We're hiring a postdoc in field robotics at the University of Pennsylvania's GRASP lab, which will focus on multi-robot autonomy, control/coordination, and perception for the DARPA Triage Challenge. #robotics
For details and to apply, see www.seas.upenn.edu/~eeaton/open...
For details and to apply, see www.seas.upenn.edu/~eeaton/open...
Open Research Positions
www.seas.upenn.edu
November 28, 2024 at 5:04 AM
We're hiring a postdoc in field robotics at the University of Pennsylvania's GRASP lab, which will focus on multi-robot autonomy, control/coordination, and perception for the DARPA Triage Challenge. #robotics
For details and to apply, see www.seas.upenn.edu/~eeaton/open...
For details and to apply, see www.seas.upenn.edu/~eeaton/open...