Right now, the Barbican Quartet plays #Mozart #Janácek #Tabakova and #Schumann in #Marl https://pst.cr/AHcYq #wch

In 20 minutes, the Barbican Quartet plays #Mozart #Janácek #Tabakova and #Schumann in #Marl https://pst.cr/AHcYq #wch

Today, the Barbican Quartet plays #Mozart #Janácek #Tabakova and #Schumann in #Marl https://www.worldconcerthall.com/en/schedule/the_barbican_quartet_plays_mozart_janacek_tabakova_and_schumann_in_marl/74690/ #wch

[https://twitter.com/michaeld1729/status/1604855967879172096?s=46&t=wxGlb03ZPSMgGiSpSUli_g | XP]
Very interesting result, showing that one can do very well on the very popular SMAC benchmark without looking at the observations!

This should be a reminder that progress in RL and MARL is hard to measure well, and even when progress is being made by a well defined metric, it is often not for the reasons we think!

#MARL #RL #reinforcementlearning

This #FollowFriday I have the following recommendations:

For useful advice regarding Mastodon
@feditips

For excellent #StreetPhotography
@omi_geek

For beautiful and unique looks into #Space
@kevinmgill

For discussion about the AI methods that can famously play Atari games:
#ReinforcementLearning
#DeepRL
#MARL
#RL

Other hashtags worth following:
#ThrowbackThursday
#FollowFriday
#Caturday

Today is the #NeurIPS2022 #DeepRL workshop, starting in just a few hours!

We have two papers there which may be of interest to #MARL #gametheory #RL researchers:

- ESCHER: Eschewing Importance Sampling in Games by Computing a History Value Function to Estimate Regret my McAleer et al. (https://openreview.net/forum?id=GMMdlnRYj4), and

- A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games by Sokota and D'Orazio et al. (https://openreview.net/forum?id=ndZ42T8iUmd),

Really happy to announce that our work on Stratego is being published in Science today!
Our agent, DeepNash, is able to play at an expert level this game of imperfect information which is more complex than chess, Go and poker.
DeepNash learned with an approach that combines game theory and model-free deep reinforcement learning. Here's how it works :
https://www.deepmind.com/blog/mastering-stratego-the-classic-game-of-imperfect-information
https://www.science.org/doi/10.1126/science.add4679
#reinforcementlearning , #MARL #gametheory @sharky6000 @karltuyls

I had to miss @NeuripsConf this year but nice to see all the photos, papers, and stories!

Any #reinforcementlearning #MARL or #gametheory papers that you liked? Would love to hear about them! :)

In New Orleans for #Neurips2022.

Monday I'll be at the affinity workshops.

Tuesday I'll be at poster session 1 for our paper Equivariant Networks for Zero-Shot Coordination (https://arxiv.org/abs/2210.12124) and at poster session 2 for our oral-designated paper Maximum Class Separation as Inductive Bias in One Matrix (https://arxiv.org/abs/2206.08704).

Happy to discuss #RL, #AI4Science, #MARL, #GeometricDL. Please feel free to reach out if you want to chat!

I am moving away from the blue bird, so it's time for an #introduction. I am a Ph.D. student at the University of Edinburgh, in Stefano Albrecht's group. My Ph.D. research is in the area of Multi-Agent Deep Reinforcement Learning #MARL. In particular, I have studied experience and parameter sharing and I am now looking into improving #reinforcementlearning algorithms for non-conflict games.

Happy to see so many familiar people here!

Wooohooo #tgif it's my third #followfriday ! I was happy to see more DeepMind, #reinforcementlearning , #MARL , #gametheory and games researchers joining #mastodon this week! :)

@MiroDudik
@chelseafinn
@karltuyls
@julien
@Yorambac
@tomzahavy
@marris
@robertarail
@BondiElizabeth
@risi
@togelius
@nicolas_le_roux
@gda
@LukasSchaefer
@diederikroijers
@hugh
@vwxyzjn
@manfreddiaz
@pdanassis

Hello world!
I’m looking for PhD positions in #MARL. My research is focused on MARL in mixed environment settings. If you’re hiring PhD students, please do reach out. I’ll also be at #NeurIPS2022 all next week and I’d be happy to chat over coffee.

(not my own work) New paper by Meta on #diplomacy #AI #MARL

https://www.google.com/amp/s/about.fb.com/news/2022/11/cicero-ai-that-can-collaborate-and-negotiate-with-you/amp/

https://youtu.be/lNtBiZaLA0k

#introduction

Hello, Mastodon!!

I am a Postdoc at Harvard in AI working to develop AI systems with positive social impact!

Previously at EPFL.

I am interested in multi-agent systems, reinforcement learning, and game theory. My work is motivated by and applied to sustainability, mobility, public health, green security.

Feel free to reach out!

#ArtificialIntelligence #AI #AIforSocialGood #MultiAgentSystems #MAS #ReinforcementLearning #RL #MARL #GameTheory #Harvard #CRCS #EPFL

Super excited to be a part of this community! I am seeking Ph.D. positions in MARL.

Looking forward to getting in touch with fellow enthusiasts in the field!

#MARL #PhD #PhDaspirant

Hello Everyone! I'm Nikunj, currently an MS student at NYU.

I am interested in multi-agent reinforcement learning, sequential decision-making, and optimization :)

#Introduction #MARL #RL

#introduction
Hi all, I do research on international political economy, macroeconomics, and applied/interpretable machine learning. I don't do a lot of posting, but I like how vibrant the #academicmastodon scene seems to be growing...

Ok, let's throw some hashtags around:
#internationalrelations #politicaleconomy #macroeconomics #institutions #ML #multiagentsystems #MARL #gametheory

It's #followfriday again! Here are more accounts to follow!

More DeepMind and #reinforcementlearning #MARL #gametheory colleagues:

@ian_goodfellow
@conitzer
@PatrickPilarski
@pfau
@felixhill
@razp
@janexwang
@996roma
@stepleton
@stephaniechan
@annakoop
@mikebjohanson
@tewalds
@encode_this
@avishkar
@DustinRMorrill
@cjdamato
@nicolas_le_roux
@Matthias

And the official NeurIPS account!

@NeuripsConf

Hi all, I am giving a talk tomorrow Thursday 4pm EST at the University of Maryland #MARL reading group.

Title: Recent Progress on Game-Theoretic Reinforcement Learning for Two-Player Zero-Sum Games.

Abstract and details to join here: https://sites.google.com/view/university-of-maryland-marl/talks/marclanctot_nov17_2022

Hope to see you there!

Last year I presented at the Graduate Research Innovative Exchange at WPI about my work on #MARL from a #swarmintelligence perspective and was awarded the Peoples Choice Award. A lot of work has been done since this presentation and I am looking forward to sharing with you all in the near future.

https://youtu.be/r0m4peF37kk