🔥Telegram İfşa

I am recruiting PhD students at Oregon State University EECS for Fall'22. Topics: Safe & Reliable AI; Foundations & Applications of Automated Planning; Human-Agent Collaboration; RL in the open world. Apply at eecs.oregonstate.edu/ai-degree-prog… by Dec 15. Happy to chat to ensure it's a mutual fit.

Delighted to be a speaker in Responsibility in AI Systems & Experiences (RAISE) seminar series! Thank you for inviting me and I look forward to presenting on Friday.

Congratulations to my Ph.D. advisor Shlomo Zilberstein on being named an ACM Fellow for his "contributions to automated planning, resource-bounded reasoning, and multi-agent systems"! Very well-deserved honor! @umasscs acm.org/media-center/2…

I'm happy to announce that NASA's Summer 2022 Internship Program includes 3 positions on the subject of automated planning and scheduling. Please have a look at the thread for listings. Deadline for applications is April 4. All applicants must be US citizens.

If you take all the fields that study intelligent decision making—from neuroscience to AI, psychology to control theory, economics to operations research—do their theories have much in common? I think so, as I explain in this new short paper: arxiv.org/pdf/2202.13252…

Honored to receive outstanding program committee member award at ICAPS Conference 2022!

New Article: "Avoiding Negative Side Effects of Autonomous Systems in the Open World" by Saisubramanian, Kamar and Zilberstein (Conference Award Track) jair.org/index.php/jair…

A little late to the party: I'm excited to announce that our paper on how to tune the hyperparameters of planning algorithms with deep RL was accepted to #ICAPS2022! Check out our paper! 1/6 justinsvegliato.com/s/BSNZicaps22.…

At the end of the spring term, I made a to-do list for my summer. I have added 7 tasks to it since then, and managed to complete only 1 so far🤔

Real world is too complex to model perfectly. Safety concerns in execution time may not follow Markov property. Our upcoming #AAAI23 paper presents a framework to learn, represent and plan to avoid non-Markovian negative side effects for reliable execution. Preprint coming soon.

There are better ways to communicate a rejection, without disrespecting the author's efforts and contributions. This is rude and can be demotivating, especially for junior researchers.

How to ensure that an RL agent learns an intended reward? How to detect and amend reward misalignment during learning? In our #IJCAI23 paper we show how an agent can improve alignment using feedback on explanations of its learned reward. ijcai.org/proceedings/20…

Thrilled to announce the first annual Reinforcement Learning Conference RL_Conference, which will be held at UMass Amherst August 9-12! RLC is the first strongly peer-reviewed RL venue with proceedings, and our call for papers is now available: rl-conference.cc.

The ICAPS 2024 Doctoral Consortium submission deadline is being pushed back to March 1st. * Students who require an early decision due to visa application should email ([email protected]) after submitting their application. icaps24.icaps-conference.org/calls/dc/

Cold emails are hard and good ones can change a life. Here is my email to Nando de Freitas that started my career in ML (at the time I was a PM at Google) docs.google.com/document/d/1_u… Real effort (incl feedback) went into drafting it. Thanks to Eugene Vinitsky 🍒🦋 for nudging me to put it online

Excited to announce the RLC best paper awards! Like last year, we wanted to highlight the many excellent ways you can do research. rl-conference.cc/RLC2025Awards.…

Honored to receive the Outstanding Paper Award at #RLC2025! Our paper WOFOSTGym brings us a step closer to applying RL to specialty crops management. If you're at RLC, come visit our talk today at 10:35am in CCIS 1-440 and our poster at 3 pm. AgAID Institute Alan Fern