Had a great time at #AAAI23 ! Thank @Riedl so much for his guidance and support!
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
AI for Behavior Change

The AAAI-23 Workshop on AI For Behavior Change held at the Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI-23)

AI4BC-23
Presented our work "Med-EASi: Finely Annotated Dataset and Models for Controllable Simplification of Medical Texts" at the @RealAAAI AISI track, today! If you missed the oral presentation, please stop by poster booth 204.
@chandraynarayan
@michiyasunaga
@fabulousQian
#AAAI23
Talk by Prof. Josh Tanenbaum! Had a good laugh about how to retrieve a ping-pong ball from underneath the couch.
#AAAI23

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 An earlier (now somewhat out of date) version of the talk is here: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

New Design Decisions for Modern AI Agents

On-demand video platform giving you access to lectures from conferences worldwide.

Underline.io
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
AAAI'23 #SE-5374 Foundations of Cooperative AI -- with captions

Screencast-O-Matic

The first author Sebastiaan De Peuter does not follow twitter but is certainly wotrh talking with - I am proud of this paper, on Collaborative AI for design problems and sequential decision making more generally. @FCAI_fi #TuringAIFellows @idsai_uom
---
RT @FCAI_fi
Sunday Feb. 12 at #AAAI23 in Washington: AI assistance + automation for solving sequential decision problems.

Paper: Zero-Shot Assistance in Sequential Decision Problems (@sami…
https://twitter.com/FCAI_fi/status/1623780021847355392

Finnish Center for AI 🐘 @[email protected] on Twitter

“Sunday Feb. 12 at #AAAI23 in Washington: AI assistance + automation for solving sequential decision problems. Paper: Zero-Shot Assistance in Sequential Decision Problems (@samikaski et al.) https://t.co/9W23fh4TgU”

Twitter
Excited to be at DC for attending #AAAI23, my first in-person conference 🤩. Looking forward to meeting wonderful people here. Thanks to my awesome collaborators (@chandraynarayan ++) and super supportive colleagues at #DDIS😇.

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

Co-Imitation: Learning Design and Behaviour by Imitation

The co-adaptation of robots has been a long-standing research endeavour with the goal of adapting both body and behaviour of a system for a given task, inspired by the natural evolution of animals. Co-adaptation has the potential to eliminate costly manual hardware engineering as well as improve the performance of systems. The standard approach to co-adaptation is to use a reward function for optimizing behaviour and morphology. However, defining and constructing such reward functions is notoriously difficult and often a significant engineering effort. This paper introduces a new viewpoint on the co-adaptation problem, which we call co-imitation: finding a morphology and a policy that allow an imitator to closely match the behaviour of a demonstrator. To this end we propose a co-imitation methodology for adapting behaviour and morphology by matching state distributions of the demonstrator. Specifically, we focus on the challenging scenario with mismatched state- and action-spaces between both agents. We find that co-imitation increases behaviour similarity across a variety of tasks and settings, and demonstrate co-imitation by transferring human walking, jogging and kicking skills onto a simulated humanoid.

arXiv.org
First in person conference several years and great to be back in D.C. Pop over to our booth if you are at #AAAI23