archimedes-Artificial Intelligence, Data Science, Algorithms-greece

 
Artificial Intelligence
 
Data Science
 
Algorithms

[Archimedes Talks Series] Can Q-learning be improved with Advice?

Dates
2024-06-12 11:00 - 13:00
Venue
Artemidos 1 - Amphitheater

Archimedes is proud to host a Talk on "Can Q-learning be improved with Advice?" by Noah Golowich(MIT) as part of our Prediction Study Group this following Wednesday at 11am.

Title: Can Q-learning be improved with Advice?

Presenter: Noah Golowich, Massachusetts Institute of Technology

Abstract: Despite rapid progress in theoretical reinforcement learning (RL) over the last few years, most of the known guarantees are worst-case in nature, failing to take advantage of structure that may be known a priori about a given RL problem at hand. In this paper we address the question of whether worst-case lower bounds for regret in online learning of Markov decision processes (MDPs) can be circumvented when information about the MDP, in the form of predictions about its optimal Q-value function, is given to the algorithm. We show that when the predictions about the optimal Q-value function satisfy a reasonably weak condition we call distillation, then we can improve regret bounds by replacing the set of state-action pairs with the set of state-action pairs on which the predictions are grossly inaccurate. This improvement holds for both uniform regret bounds and gap-based ones. Further, we are able to achieve this property with an algorithm that achieves sublinear regret when given arbitrary predictions (i.e., even those which are not a distillation). Our work extends a recent line of work on algorithms with predictions, which has typically focused on simple online problems such as caching and scheduling, to the more complex and general problem of reinforcement learning. 

Bio: Noah Golowich (Massachusetts Institute of Technology) was advised by Constantinos Daskalakis and Ankur Moitra. He completed his A.B. and S.M. at Harvard University. His research interests lie in theoretical machine learning, with a particular focus on the connections between multi-agent learning, game theory, and online learning, and in theoretical reinforcement learning. He is supported by a Fannie & John Hertz Foundation Fellowship and an NSF Graduate Fellowship.

 

________________________________________________________________________________
Microsoft Teams Need help?
Meeting ID: 373 512 132 356
Passcode: 9bUg8w
For organizers: Meeting options
 
 
________________________________________________________________________________
 
 

Vision

To position Greece as a leading player in AI and Data Science

image
image

Mission

To build an AI Excellence Hub in Greece where the international research community can connect, groundbreaking ideas can thrive, and the next generation of scientists emerges, shaping a brighter future for Greece and the world

 

Welcome to ARCHIMEDES, a vibrant research hub connecting the global AI and Data Science research community fostering groundbreaking research in Greece and beyond. Its dedicated core team, comprising lead researchers, affiliated researchers, Post-Docs, PhDs and interns, is committed to advancing basic and applied research in Artificial Intelligence and its supporting disciplines, including Algorithms, Statistics, Learning Theory, and Game Theory organized around 8 core research areas. By collaborating with Greek and Foreign Universities and Research Institutes, ARCHIMEDES disseminates its research findings fostering knowledge exchange and providing enriching opportunities for students. Leveraging AI to address real-world challenges, ARCHIMEDES promotes innovation within the Greek ecosystem and extends its societal impact. Established in January 2022, as a research unit of the Athena Research Center with support from the Committee Greece 2021, ARCHIMEDES is funded for its first four years by the EU Recovery and Resilience Facility (RRF).

 
 

NEWS

 
6 Accepted Papers at ICLR 2026

6 Accepted Papers at ICLR 2026

11 March 2026

The Archimedes research unit of the Athena Research Center in Greece has six papers accepted at this year's International Conference on Learning Representations (ICLR) gathering, including one oral presentation. The acceptance rate for posters was about 25,8% and about 1,1% for oral presentations.  Please bear in mind that ICLR, along with NeurIPS and ICML, is considered one of the three top-tier artificial intelligence and machine learning conferences in the world.

Former Archimedes Intern Receives the EETN Best Doctoral Thesis Award for 2025

Former Archimedes Intern Receives the EETN Best Doctoral Thesis Award for 2025

9 March 2026

Georgios Papasotiropoulos, a former intern of the Archimedes unit of the Athena Research Center, Greece, received the Hellenic Artificial Intelligence Society's (EETN) Best Doctoral Thesis Award for the year 2025. His doctoral thesis was on "Algorithmic and Game-Theoretic Aspects of Computational Social Choice" and his supervisor was Vangelis Markakis, a Professor at the Department of Informatics of the Athens University of Economics & Business (AUEB), Greece and a Lead Researcher at the Archimedes research unit in AI, Data Sciences, and Algorithms of the Athena Research Center in Athens, Greece.

Archimedes Seminar by Nikos Paragios on

Archimedes Seminar by Nikos Paragios on "Seeing the Invisible - Doing the Impossible: AI-powered diagnosis, treatment and beyond"

12 February 2026

On Monday 16 February, 2026, from 2:00 pm to 3:30 pm, at the Archimedes Amphitheatre (1 Artemidos Street, 15125, Marousi, Archimedes, Athena Research Center, Greece), Professor Nikos Paragios, Distinguished Professor of Mathematics, University of Paris-Saclay, France, and Chief Executive and Technical Officer, TheraPanacea, Paris, France, will deliver an Archimedes Seminar on "Seeing the Invisible - Doing the Impossible: AI-powered diagnosis, treatment and beyond".

Τhe Ambassador of Australia to Greece visits Archimedes!

Τhe Ambassador of Australia to Greece visits Archimedes!

11 February 2026

On Wednesday, 11 February 2026, the Ambassador of Australia to Greece, Mrs. Alison Duncan, visited the Archimedes Research Unit at the Athena Research Center in Greece and had a very productive meeting with Professor Timos Sellis, Director of the Archimedes Research Unit.

Archimedes AGT Afternoon Event (ΑAGTA) will take place on 4 February 2026 at Archimedes premises

Archimedes AGT Afternoon Event (ΑAGTA) will take place on 4 February 2026 at Archimedes premises

2 February 2026

Archimedes AGT Afternoon Event (ΑAGTA) is a newly-established scientific event, focusing on Algorithmic Game Theory and Artificial Intelligence. The first AAGTA workshop will take place on 4 February 2026 at the Archimedes Amphitheatre at Archimedes Unit, Athena Reseach Center, Greece, and will feature two keynote speeches: one by Prof. Paul Goldberg of the University of Oxford, UK, and one by Prof. Christos Papadimitriou of Columbia University, USA and Archimedes Unit, Athena Reseach Center, Greece.

More news items here
 
 

The project “ARCHIMEDES Unit: Research in Artificial Intelligence, Data Science and Algorithms” with code OPS 5154714 is implemented by the National Recovery and Resilience Plan “Greece 2.0” and is funded by the European Union – NextGenerationEU.

greece2.0 eu_arch_logo_en

 

Stay connected! Subscribe to our mailing list by emailing sympa@lists.athenarc.gr
with the subject "subscribe archimedes-news Firstname LastName"
(replace with your details)