I’m honored to serve as Managing Director of the new NSF AI Institute for Human-AI Cooperation (HAIC), developing adaptive, collaborative, and trustworthy AI systems designed to strengthen human decision-making. @haicinstitute.bsky.social penntoday.upenn.edu/news/penn-pa...

Penn partners in new National Science Foundation AI Institute for Human-AI Cooperation | Penn Today

Funded by a $21.5 million, five-year award, NSF HAIC will focus on pioneering AI’s role in improving healthcare.

penntoday.upenn.edu

A huge congratulations to @marcelhussing.bsky.social, who successfully defended his dissertation, “Algorithm Output Stability in Reinforcement Learning,” earlier today at Penn. Way to go, Dr. Hussing!! @pennengineering.bsky.social @grasplab.bsky.social

In emergencies, minutes can decide who lives and who dies. Our team is participating in the Triage Challenge, building AI to empower clinicians and prioritize care when resources are thin: prontotriage.com Also recently featured by Meta: ai.meta.com/blog/upenn-d... (1/5)

🎉 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

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

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

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

📢 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

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

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.

@ericeaton.bsky.social · 2y ago

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...

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.

Chris Person@papapishu.bsky.social · 2y ago

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-...

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

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

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.

Come join us in Philadelphia in August for CoLLAs 2025!

Shagun Sodhani@shagunsodhani.bsky.social · 2y ago

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

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...