Anna Hakhverdyan

Heading to ICLR to present our work on learning dynamics in continuous control. We derive, to our knowledge, one of the first parametric models of reinforcement learning whose theory closely tracks what we observe in practice. My favorite figure: empirical theoretical match.

Learning accurate World Models for long horizon planning is hard. So what minimal aspect of world dynamics must a model capture to achieve complex goals? We find a simple and effective solution in our #ICLR2026 paper, which we will present as an Oral at @worldmodel_26. (1/n)

Can robots learn data-efficient world models for object manipulation? Our new paper, which won "Best Paper" at the @corl_conf RINO Workshop, shows how robots learn object-centric world models with just a few minutes of interaction data. 🧵1/7

Meet the recipients of the 2024 ACM A.M. Turing Award, Andrew G. Barto and Richard S. Sutton! They are recognized for developing the conceptual and algorithmic foundations of reinforcement learning. Please join us in congratulating the two recipients! bit.ly/4hpdsbD

BREAKING: Amii Chief Scientific Advisor, Richard S. Sutton, has been awarded the A.M. Turing Award, the highest honour in computer science, alongside Andrew Barto! Read the official @TheOfficialACM announcement: hubs.la/Q039nZXM0 #TuringAward #AI #ReinforcementLearning

Some extra motivation for those of you in RLC deadline mode: our line-up of keynote speakers -- as all accepted papers get a talk, they may attend yours!

RLC will be held at the Univ. of Alberta, Edmonton, in 2025. I'm happy to say that we now have the conference's website out: rl-conference.cc/index.html We'll continue to update it, and the CFP will be out soon, but the relevant dates are already there. @RL_Conference @UAlberta

“Nature never appeals to intelligence until habit and instinct are useless. There is no intelligence where there is no change and no need of change.” —H. G. Wells, The Time Machine

"In the Beginning, ML was RL". Andrew Barto gave RLC 2024 an amazing overview of the intertwined history of ML and RL (Link below)

E58: RLC 2024 - Posters and Hallways 3 Recorded at @RL_Conference 2024. Featuring: 0:01 @m33pinator from Openmind on Time Discretization 2:23 @anna_ssi_ from @UAlberta on Online Hyperparameters 3:59 @Dilip_Arumugam from @Princeton on Information Theory and Exploration 5:04 @MicahCarroll from @UCBerkeley on Changing preferences and AI alignment

Yesterday there was a completely-student-organized summit of the RLAI (Reinforcement Learning and Artificial Intelligence) research group at the University of Alberta, held at the lovely Amii headquarters. Nice folks and diverse new ideas!

When deep learning #AI goes shallow... nature.com/articles/s4158… @RichardSSutton @s_dohare @Nature nature.com/articles/d4158… @clarelyle @NatureNV Loss of plasticity, catastrophic forgetting can occur with task switching, inability for new learning

Please repost or retweet this message and use the hashtags #Armenia #StandWithArmenia