#aaai23 — Public Fediverse posts

looking forward to participating on this panel on "Reinforcing Preferences vs Behavior Change" at #AAAI23 (at 2pm in room 140A)
https://ai4bc.github.io/ai4bc23/#panelists

Excited to give my talk "New Design Decisions for Modern AI Agents" at #AAAI23 tomorrow (Sunday) morning at 8:30am in Ballroom ABC! An earlier (now somewhat out of date) version of the talk is here:

https://underline.io/lecture/18450-keynote-vincent-conitzer---new-design-decisions-for-modern-ai-agents

Excited to present our blue sky paper "Foundations of Cooperative AI" at #AAAI23 tomorrow (Friday, at the end of the 2-3:15pm session, room 202B). You can see the 15-minute pre-recording here (use CC->english-1 for captions):
https://screencast-o-matic.com/watch/c0Ve3hVwj62
paper: https://www.cs.cmu.edu/~conitzer/FOCALAAAI23.pdf

Are you at #AAAI23 this week? Check out these papers from FCAI:

*️⃣ Co-Imitation: Learning Design and Behaviour by Imitation (Rajani et al.) https://arxiv.org/abs/2209.01207 (project website https://sites.google.com/view/co-imitation)

*️⃣ Zero-Shot Assistance in Sequential Decision Problems (@samikaski et al.)
https://arxiv.org/abs/2202.07364

Are you at #AAAI23 this week? Check out these papers from FCAI:

*️⃣ Co-Imitation: Learning Design and Behaviour by Imitation (Rajani et al.) https://arxiv.org/abs/2209.01207 (project website https://sites.google.com/view/co-imitation)

*️⃣ Zero-Shot Assistance in Sequential Decision Problems (@samikaski et al.)
https://arxiv.org/abs/2202.07364

Friends, I'll be in Washington, DC attending #AAAI23 in the coming days. Let me know if you're also attending the conference and if you'd like to meet!

A 2-day workshop, “Systems Neuroscience Approach to General Intelligence”, will be held at AAAI-23 in DC on Feb 13-14.

For latest information about the workshop, and how to join, see https://ibm.co/3hnf8t1

#aaai23 #neuroscience #AGI #intelligence #consciousness

A 2-day workshop, “Systems Neuroscience Approach to General Intelligence”, will be held at AAAI-23 in DC on Feb 13-14.

For latest information about the workshop, and how to join, see https://ibm.co/3hnf8t1

#aaai23 #neuroscience #AGI #intelligence #consciousness

Trying to identify some of the key topics people work on in #AI. Of course #ML is popular, but I’m trying to think of other core topics, such as knowledge representation, planning, reasoning, search, heuristics, etc. the #AAAI23 conference also emphasizes “natural language processing, computer vision, data mining, multiagent systems, knowledge representation, human-in-the-loop AI, search, planning, reasoning, robotics and perception, and ethics.” Any other topics I’m missing?

Trying to identify some of the key topics people work on in #AI. Of course #ML is popular, but I’m trying to think of other core topics, such as knowledge representation, planning, reasoning, search, heuristics, etc. the #AAAI23 conference also emphasizes “natural language processing, computer vision, data mining, multiagent systems, knowledge representation, human-in-the-loop AI, search, planning, reasoning, robotics and perception, and ethics.” Any other topics I’m missing?

A 2-day workshop, “Systems Neuroscience Approach to General Intelligence”, will be held
@RealAAAI -23 in DC on Feb 13-14. For more information about the workshop, and how to join, see https://ibm.co/3hnf8t1 #aaai23 #neuroscience #AGI

A 2-day workshop, “Systems Neuroscience Approach to General Intelligence”, will be held
@RealAAAI -23 in DC on Feb 13-14. For more information about the workshop, and how to join, see https://ibm.co/3hnf8t1 #aaai23 #neuroscience #AGI

To appear at AAAI 2023 #AAAI23 #AAAI2023, Fairness Concepts for Indivisible Items with Externalities. Haris Aziz, Warut Suksompong, Zhaohong Sun, Toby Walsh. See you in DC! https://arxiv.org/abs/2110.09066

Reviewing for #AAAI23 has been a frustrating experience.

Several papers use #ML to solve complex problems. E.g, a conversational system for helping a user find a restaurant. However, the entire paper is consumed in maths about Jacobians/second-order derivative of Lagrange (not original).

But, there is no problem formulation. No discussion on why a specific RL approach is useful for the problem. Or, why adversarial networks are relevant. No hypothesis about user interaction.