[UAI] PostDoc on Reinforcement Learning in the Real World @ TU Delft

[Frans Oliehoek]

(apologies for cross posting)

At Delft University of Technology, we have a vacancy for a

3 year PostDoc on Reinforcement Learning in the Real World

This is in the context of the Mercury Machine Learning Lab, jointly with 
the University of Amsterdam and booking.com. We will focus on 
fundamental techniques in reinforcement learning, moticated by 
real-world problems. Possible directions of interest are:


Bayesian reinforcement learning
Multiagent / concurrent reinforcement learning
Causal reinforcement learning

Full vacancy text can be found here:

https://www.tudelft.nl/over-tu-delft/werken-bij-tu-delft/vacatures/details?jobId=6407&jobTitle=PostDoc%20on%20Reinforcement%20Learning%20in%20the%20Real%20World%20%20%20%20%20%20%20%20%20

Please forward to potential candidates, and contact Matthijs Spaan or 
myself in case of questions.




--
___
Dr. Frans Oliehoek
Associate Professor
Delft University of Technology
E-mail: f.a.olieh...@tudelft.nl
www.fransoliehoek.net
___
uai mailing list
uai@engr.orst.edu
https://it.engineering.oregonstate.edu/mailman/listinfo/uai

[UAI] Challenges and Opportunities in Multiagent RL: Branislav Bosansky

[Frans Oliehoek]

Dear all,


Happy to announce the next speaker in our virtual seminars on the 
Challenges and Opportunities for Multiagent Reinforcement Learning (COMARL):



Speaker: Branislav Bosansky

Title: Solving Dynamic Games with Imperfect Information

When: November 18th


Abstract:

Finding optimal strategies for dynamic multi-agent interactions, where 
agents have only partial observations about the environment, is one of 
today's challenges. Even the cases with two agents and strictly 
competitive interactions (i.e., zero-sum games) are difficult -- 
especially if we consider interactions that either require many turns to 
complete or do not have a limited number of turns. At the same time, we 
want algorithms with bounded error to know how close to (or far away 
from) the optimum the found strategies are.



 From the game-theoretic perspective, we can model two-agent strictly 
competitive interactions as zero-sum partially observable stochastic 
games (zs-POSGs) with the infinite or indefinite horizon. Since even 
zs-POSGs can be undecidable, we pose further restrictions that allow us 
to design and implement search algorithms that are guaranteed to 
converge to optimal strategies and have a bounded error. Our algorithms 
are inspired by Heuristic Search Value Iteration (HSVI) for 
partially-observable Markov decision processes (POMDPs), however, 
significantly modified to solve games where (a) only one player has 
partial information or (b) where both players have partial information 
but all observations are public.



In the talk, I will describe the key characteristics and the schema of 
all of our algorithms and identify future directions to scale up and/or 
generalize our algorithms.



Date & time: November 18th 10AM EDT / 3PM UTC / 4PM CET

How to 
attend:https://sites.google.com/view/comarl-seminars/how-to-attend 
<https://sites.google.com/view/comarl-seminars/how-to-attend>



Calendar with talks and Google Meet 
links:https://calendar.google.com/calendar/u/0?cid=Y19uZm9xdHZvZWw3Z3R0NDg0aGduZDUxc3U1NEBncm91cC5jYWxlbmRhci5nb29nbGUuY29t 
<https://calendar.google.com/calendar/u/0?cid=Y19uZm9xdHZvZWw3Z3R0NDg0aGduZDUxc3U1NEBncm91cC5jYWxlbmRhci5nb29nbGUuY29t>



We look forward to seeing you there!


Best regards from the organizers,


Chris Amato (Northeastern University),

Marta Garnelo (DeepMind),

Robert Loftin (TU Delft),

Frans Oliehoek (TU Delft),

Shayegan Omidshafiei (Google),

Karl Tuyls (DeepMind)

___
uai mailing list
uai@engr.orst.edu
https://it.engineering.oregonstate.edu/mailman/listinfo/uai

[UAI] Two funded PhD positions on Reinforcement Learning in the Real World at TU Delft

[Frans Oliehoek]

(apologies for cross-posting)

Do you have what it takes to push reinforcement learning beyond the 
realm of games?


TU Delft (Netherlands) offers 2 PhD positions focusing on reinforcement 
learning in the recently established Mercury Machine Learning Lab 
(MMLL). In this lab, researchers from the University of Amsterdam and 
Delft University of Technology will be working together with data 
scientists from Booking.com to develop more usable reinforcement 
learning and other machine learning techniques.


Reinforcement learning is a promising approach to learn to control 
decision making problems that extend over time, but so far applications 
have been largely limited to synthetic settings such as games. Motivated 
by real-world problems faced in industry, we will investigate 
fundamental problems in reinforcement learning. For instance, we will 
study effective exploration in non-stationary environments and learning 
using many parallel trials. The candidates will be jointly supervised by 
Dr. M.T.J. Spaan and Dr. F.A. Oliehoek.


The MMLL collaboration provides the unique opportunity to test AI 
techniques in the real world, allowing new machine learning methods to 
be safely developed for wide application, for example in mobility, 
energy or healthcare. In addition to the existing researchers, the 
Mercury Machine Learning Lab will comprise six PhD candidates and two 
postdocs who will work on six different projects related to bias and 
generalisation problems over the course of the next five years.


Further details and an application form can be found via the following 
links.

https://icai.ai/mercury-machine-learning-lab/
https://www.tudelft.nl/over-tu-delft/werken-bij-tu-delft/vacatures/details?jobId=3533&jobTitle=2%20PhD%20Positions%20on%20Reinforcement%20Learning%20in%20the%20Real%20World

Application deadline for full consideration: 23 August 2021

Informal enquiries: Matthijs Spaan (m.t.j.sp...@tudelft.nl) and Frans 
Oliehoek (f.a.olieh...@tudelft.nl).


___
uai mailing list
uai@engr.orst.edu
https://it.engineering.oregonstate.edu/mailman/listinfo/uai

[UAI] Craig Boutilier @ Challenges and Opportunities in Multiagent RL

[Frans Oliehoek]

Dear all,


After a fantastic inaugural presentation by Michael Bowling, we are 
excited to announce the next speaker in our virtual seminar series on 
the Challenges and Opportunities for Multiagent Reinforcement Learning 
(COMARL):



Speaker: Craig Boutilier, Google Research

Title: Maximizing User Social Welfare in Recommender Ecosystems

(abstract and bio can be found below)


Date: Thursday February 11th, 2021

Time: 17:00 CET / 16:00 UTC / 08:00 PST

Location: via google meet or youtube


For detailed instructions on how to join, please see here:

https://sites.google.com/view/comarl-seminars/how-to-attend


For additional information, please see our:

 *

   Website <https://sites.google.com/view/comarl-seminars>(includes
   schedule, instructions on how to join, etc.)

 *

   Twitter account (for speaker announcements and
   more!):@ComarlSeminars <https://twitter.com/ComarlSeminars>

 *

   Google Groups (to receive invitations):
   comarlsemin...@googlegroups.com <mailto:comarlsemin...@googlegroups.com>


We look forward to seeing you there!


Best regards from the organizers,


Chris Amato (Northeastern University),

Marta Garnelo (DeepMind),

Frans Oliehoek (TU Delft),

Shayegan Omidshafiei (DeepMind),

Karl Tuyls (DeepMind)




Speaker:

Craig Boutilier

Google Research,

Mountain View, CA, USA


Title:

Maximizing User Social Welfare in Recommender Ecosystems


Abstract:

An important goal for recommender systems is to make recommendations 
that maximize some form of user utility over (ideally, extended periods 
of) time. While reinforcement learning has started to find limited 
application in recommendation settings, for the most part, practical 
recommender systems remain "myopic" (i.e., focused on immediate user 
responses). Moreover, they are "local" in the sense that they rarely 
consider the impact that a recommendation made to one user may have on 
the ability to serve other users. These latter "ecosystem effects" play 
a critical role in optimizing long-term user utility. In this talk, I 
describe some recent work we have been doing to optimize user utility 
and social welfare using reinforcement learning and equilibrium modeling 
of the recommender ecosystem; draw connections between these models and 
notions such as fairness and incentive design; and outline some future 
challenges for the community.



Bio:

Craig Boutilier is a Principal Scientist at Google. He received his 
Ph.D. in Computer Science from U. Toronto (1992), and has held positions 
at U. British Columbia and U. Toronto (where he served as Chair of the 
Dept. of Computer Science). He co-founded Granata Decision Systems, 
served as a technical advisor for CombineNet, Inc., and has held 
consulting/visiting professor appointments at Stanford, Brown, CMU and 
Paris-Dauphine.


Boutilier's current research focuses on various aspects of decision 
making under uncertainty, including: recommender systems; user modeling; 
MDPs, reinforcement learning and bandits; preference modeling and 
elicitation; mechanism design, game theory and multi-agent decision 
processes; and related areas. Past research has also dealt with: 
knowledge representation, belief revision, default reasoning and modal 
logic; probabilistic reasoning and graphical models; multi-agent 
systems; and social choice.



Boutilier served as Program Chair for IJCAI-09 and UAI-2000, and as 
Editor-in-Chief of the Journal of AI Research (JAIR). He is a Fellow of 
the Royal Society of Canada (FRSC), the Association for Computing 
Machinery (ACM) and the Association for the Advancement of Artificial 
Intelligence (AAAI). He also received the 2018 ACM/SIGAI Autonomous 
Agents Research Award.


___
uai mailing list
uai@engr.orst.edu
https://it.engineering.oregonstate.edu/mailman/listinfo/uai

[UAI] 3 year postdoc at Delft University of Technology

[Frans Oliehoek]

(apologies for cross-posting)

We are pleased to announce that the Department of Intelligent Systems at 
TU Delft, The Netherlands, can offer a 3-year postdoc position, as part 
of the "Hybrid Intelligence" project,  www.hybrid-intelligence-centre.nl.


Closing date: January 8th


--

Postdoc in (Meta-)Learning to Give Feedback in Interactive Learning (3 
years)


How can an intelligent learn to interact? How can it learn via 
interaction? For this project we are looking for a postdoc who wants to 
push machine learning beyond traditional settings that assume a fixed 
dataset. Specifically, in this project we will investigate interactive 
learning settings in which two or more learners interact by giving each 
other feedback to reach an outcome that is desirable from a system 
designers perspective. The goal is to better understand how to structure 
interactions to effectively progress to the desirable outcome state, and 
to develop practical learning techniques and algorithms that exploit 
these generated insights.


The postdoc will be based at TU Delft and co-supervised by Herke van 
Hoof (University of Amsterdam) and myself. Given that the successful 
candidate will have to work with 2 supervisors at different 
institutions, we are looking for someone who can operate quite 
independently.


Full requirements and application instructions:

https://www.academictransfer.com/en/295565/postdoc-meta-learning-to-give-feedback-in-interactive-learning/


More information:

For more information, please see:

https://www.fransoliehoek.net/wp/vacancies/


Informal inquiries are welcome and can be directed to myself:
Dr. Frans Oliehoek .


--

I would be grateful if you could forward this message to suitable 
candidates.


Best regards,
-Frans Oliehoek
___
uai mailing list
uai@engr.orst.edu
https://it.engineering.oregonstate.edu/mailman/listinfo/uai

[UAI] 3-year postdoc at Delft University of Technology

[Frans Oliehoek]

I am pleased to announce that the Department of Intelligent Systems at
TU Delft, The Netherlands, can offer a 3-year postdoc position, as part
of the "Hybrid Intelligence" project,  www.hybrid-intelligence-centre.nl.

Closing date: September 1st.


--


*Postdoc in (Meta-)Learning to Give Feedback in Interactive Learning*
*(3 years)*

How can an intelligent learn to interact? How can it learn via
interaction? For this project we are looking for a postdoc who wants to
push machine learning beyond traditional settings that assume a fixed
dataset. Specifically, in this project we will investigate interactive
learning settings in which two or more learners interact by giving each
other feedback to reach an outcome that is desirable from a system
designers perspective. The goal is to better understand how to structure
interactions to effectively progress to the desirable outcome state, and
to develop practical learning techniques and algorithms that exploit
these generated insights.

The postdoc will be co-supervised by Herke van Hoof (University of
Amsterdam) and myself.

Full requirements and application instructions:

https://www.academictransfer.com/nl/293007/postdoc-meta-learning-to-give-feedback-in-interactive-learning/


*More information:*

For more information, please see:

https://www.fransoliehoek.net/wp/vacancies/


Informal inquiries are welcome and can be directed to myself:
Dr. Frans Oliehoek mailto:f.a.olieh...@tudelft.nl>>.



--

I would be grateful if you could forward this message to suitable
candidates.

Best regards,
-Frans Oliehoek


signature.asc
Description: OpenPGP digital signature
___
uai mailing list
uai@engr.orst.edu
https://it.engineering.oregonstate.edu/mailman/listinfo/uai

[UAI] Postdoc at TU Delft: Influence-based Abstraction, Learning and Coordination

[Frans Oliehoek]

I am pleased to announce that the Department of Intelligent Systems at
TU Delft, The Netherlands, can offer a postdoc position, as part of an
ERC-funded research project, "INLFUENCE: Influence-based decision-making
in uncertain environments".

Closing date: September 17.


--

*Project description:*

INFLUENCE is situated in the intersection of machine learning,
reinforcement learning and multiagent systems. The aim of the project is
to investigate how to scale up methods for automated decision making for
complex systems.

In particular, we will focus on using machine learning techniques to
learn representations of 'influence' (e.g. how certain parts of the
system affect other parts), and using such representations to scale up
decision making. INFLUENCE will focus on two problems domains:
-coordinated control of traffic lights in a large city
-autonomous warehousing with teams of robots
(But also other domains can be considered).

Currently I am recruiting for the following position:

*
*

*Postdoc in Influence-based Abstraction, Learning and Coordinatio**n*
*(3 years)*

This position will focus on algorithmic and theoretical aspects of
decision making under uncertainty and multiagent learning and
coordination. The candidate should have an excellent track record in the
general area of machine learning, reinforcement learning or planning
under uncertainty, as evidenced by publications at top-tier venues, and
should have demonstrable experience in theoretical analysis of
algorithms (e.g., proving approximation or sample bounds).

Full requirements and application instructions:

https://www.academictransfer.com/en/46318/postdoc-in-influence-based-abstraction-learning-and-coordination/


*More information:*

For more information, please see:
https://www.fransoliehoek.net/wp/vacancies/
<https://www.fransoliehoek.net/wp/vacancies/>

(in addition to the aforementioned post-specific URLs.)

Informal inquiries are welcome and can be directed to myself:
Dr. Frans Oliehoek mailto:f.a.olieh...@tudelft.nl>>.




--

I would be grateful if you could forward this message to suitable
candidates.

Best regards,
-Frans Oliehoek

___
uai mailing list
uai@ENGR.ORST.EDU
https://secure.engr.oregonstate.edu/mailman/listinfo/uai

[UAI] Postdoc vacancy at TU Delft

[Frans Oliehoek]

I am pleased to announce that the Department of Intelligent Systems at
TU Delft, The Netherlands, can offer a 3-year postdoc position, as part
of an ERC-funded research project, "INLFUENCE: Influence-based
decision-making in uncertain environments".

Closing date: September 17.


--

*Project description:*

INFLUENCE is situated in the intersection of machine learning,
reinforcement learning and multiagent systems. The aim of the project is
to investigate how to scale up methods for automated decision making for
complex systems.

In particular, we will focus on using machine learning techniques to
learn representations of 'influence' (e.g. how certain parts of the
system affect other parts), and using such representations to scale up
decision making. INFLUENCE will focus on two problems domains:
-coordinated control of traffic lights in a large city
-autonomous warehousing with teams of robots
(But also other domains can be considered).

Currently I am recruiting for the following position:

*
*

*Postdoc in Influence-based Abstraction, Learning and Coordinatio**n*
*(3 years)*

This position will focus on algorithmic and theoretical aspects of
decision making under uncertainty and multiagent learning and
coordination. The candidate should have an excellent track record in the
general area of machine learning, reinforcement learning or planning
under uncertainty, as evidenced by publications at top-tier venues, and
should have demonstrable experience in theoretical analysis of
algorithms (e.g., proving approximation or sample bounds).

Full requirements and application instructions:
https://www.academictransfer.com/en/46318/postdoc-in-influence-based-abstraction-learning-and-coordination/
<https://www.academictransfer.com/employer/TUD/vacancy/46317/lang/en/>


*More information:*

For more information, please see:
https://www.fransoliehoek.net/wp/vacancies/

(in addition to the aforementioned post-specific URLs.)

Informal inquiries are welcome and can be directed to myself:
Dr. Frans Oliehoek mailto:f.a.olieh...@tudelft.nl>>.


Also feel free to approach me during IJCAI.


--

I would be grateful if you could forward this message to suitable
candidates.

Best regards,
-Frans Oliehoek
___
uai mailing list
uai@ENGR.ORST.EDU
https://secure.engr.oregonstate.edu/mailman/listinfo/uai

[UAI] PhD and postdoc vacancies at TU Delft

[Frans Oliehoek]

I am pleased to announce that the Department of Intelligent Systems at TU
Delft, The Netherlands, can offer two PhD and one postdoc position. The
positions are part of an ERC-funded research project, "INLFUENCE:
Influence-based decision-making in uncertain environments", and are fully
funded.

Closing date: April 23.

*Project description:*
INFLUENCE is situated in the intersection of machine learning,
reinforcement learning and multiagent systems. The aim of the project is to
investigate how to scale up methods for automated decision making for
complex systems.

In particular, we will focus on using machine learning techniques to learn
representations of 'influence' (e.g. how certain parts of the system affect
other parts), and using such representations to scale up decision making.
INFLUENCE will focus on two problems domains:
-coordinated control of traffic lights in a large city
-autonomous warehousing with teams of robots
(But also other domains can be considered).

Currently I am recruiting for the following positions:

---
*PhD student in Machine Learning of Influence Descriptions in Complex
Systems  (4 years)*

This position will focus on learning compact descriptions of ‘influence’,
i.e., how a sub-problem is affected over time, by building on
state-of-the-art (deep) machine learning techniques.

Full requirements and application instructions:
https://www.academictransfer.com/employer/TUD/vacancy/46297/lang/en/


---
*PhD student in Influence-based Sequential Decision Making (4 years)*

This position will focus online planning methods (such as extensions of
Monte Carlo tree search methods) making use of learned influence
descriptions, and developing self-improving simulators.

Full requirements and application instructions:
https://www.academictransfer.com/employer/TUD/vacancy/46314/lang/en/


---
*Postdoc in High Performance Planning and Learning Algorithms (3 years)*

This position focuses on high-performance simulation-based planning and
learning, and the candidate will play a leading role in the joint
development efforts.

Full requirements and application instructions:
https://www.academictransfer.com/employer/TUD/vacancy/46317/lang/en/


---
For more information, please see:
https://www.fransoliehoek.net/wp/vacancies/

(in addition to the aforementioned post-specific URLs.)

Informal inquiries are welcome and can be directed to myself:
Dr. Frans Oliehoek .


---
Additionally, I'd like to point out that the department is also looking for
a:

*6-Year PhD Students in Computer Science with Teaching Responsibilities *

https://www.academictransfer.com/employer/TUD/vacancy/46059/lang/en/

If you have a proposal that connects to my research interests, then I am
happy to discuss.


I would be grateful if you could forward this message to suitable
candidates.

Best regards,
-Frans Oliehoek
___
uai mailing list
uai@ENGR.ORST.EDU
https://secure.engr.oregonstate.edu/mailman/listinfo/uai

[UAI] PhD position: Deep Learning for Personalised Education

[Frans Oliehoek]

(apologies for cross posting)

I am happy to announce funding for a PhD student is available at the
Department of Computer Science at the University of Liverpool:

project: Deep Learning for Personalised Education
closing date: Tuesday, December 19, 2017
url: https://www.findaphd.com/search/ProjectDetails.aspx?PJID=92569

Project Description
This project will develop and apply state-of-the-art Machine Learning
techniques to the delivery of higher education. We will use very rich time
series data about many aspects of student assessment and development. The
data is provided by our project partner LiftUpp Ltd (
https://www.liftupp.com/). The project will focus on two key tasks in this
domain: predicting student performance and calibrating assessments.

For predicting student performance, we will develop state of art sequential
prediction methods. This would allow early intervention in problematic
cases, improved student feedback, and improved assessment and training for
students. For instance, we will explore Deep Learning techniques, like
Recurrent Neural Networks. For calibration of assessments by different
staffs, we will develop and apply collaborative filtering techniques. We
will also investigate how the techniques we develop for the two tasks can
be integrated.
This project will be supervised by Frans Oliehoek (
http://www.fransoliehoek.net/) and Rahul Savani (http:/
http://www.csc.liv.ac.uk/~rahul). In addition to your formal application,
please email Frans and Rahul with your CV and a short email to introduce
yourself.

Please email both Frans and Rahul with any informal enquiries:
frans.olieh...@liverpool.ac.uk and rahul.sav...@liverpool.ac.uk


Funding Notes

This PhD Studentship (Tuition fees + stipend of £ 14,553 annually over 4
years) is funded by the University of Liverpool and is available for
Home/EU students.
___
uai mailing list
uai@ENGR.ORST.EDU
https://secure.engr.oregonstate.edu/mailman/listinfo/uai

[UAI] Postdoc in Deep Learning & Simulation-based Planning, Liverpool

[Frans Oliehoek]

Postdoc in Deep Learning & Simulation-based Planning
Dept. of Computer Science, University of Liverpool

Tenure: 12 months initially
Closing Date: 21 November 2017
URL:
https://recruit.liverpool.ac.uk/pls/corehrrecruit/erq_jobspec_details_form.jobspec?p_id=008282


I am pleased to announce that the Department of Computer Science of the
University of Liverpool can offer a position for a Postdoctoral Research
Associate. The post is part of an EPSRC-funded research project, "Learning
to Efficiently Plan in Flexible Distributed Organisations", and involves a
collaboration with Northeastern University.


This project is situated in the intersection of machine learning,
multiagent systems and high-performance computing. It aims to develop new
algorithms for decision making based on a combination of deep learning and
simulation-based planning, such as Monte Carlo tree search.

The ideal candidate has:

-A PhD in Artificial Intelligence, Computer Science, Mathematics or related
discipline
-Experience with reinforcement learning techniques (and ideally Monte Carlo
tree search)
-Experience with deep learning
-Very strong programmings skills and experience with C/C++
-An excellent research track record


The full job description can be found at:
https://recruit.liverpool.ac.uk/pls/corehrrecruit/erq_jobspec_details_form.jobspec?p_id=008282

Informal inquiries are welcome and can be directed to myself:
Dr. Frans Oliehoek 


I would be grateful if you could forward this message to suitable
candidates.

Best regards,
-Frans Oliehoek


_______
Dr. Frans Oliehoek
University of Liverpool
Dept of Computer Science
Ashton Building, Ashton St
Liverpool, L69 3BX, U.K.

E-mail: f...@liverpool.ac.uk
___
uai mailing list
uai@ENGR.ORST.EDU
https://secure.engr.oregonstate.edu/mailman/listinfo/uai

[UAI] CfP: Learning, Inference, and Control of Multi-Agent Systems (MALIC)

[Frans Oliehoek]

(apologies for cross-posting)

CfP: Learning, Inference, and Control of Multi-Agent Systems
(MALIC)https://sites.google.com/site/malicaaai2018/

Description:

We live in a multi-agent world. To be successful in that world,
intelligent agents need to learn to consider the agency of others.
They will compete in marketplaces, cooperate in teams, communicate
with others, coordinate their plans, and negotiate outcomes. Examples
include self-driving cars interacting in traffic, personal assistants
acting on behalf of humans and negotiating with other agents, swarms
of unmanned aerial vehicles, financial trading systems, robotic teams,
and household robots.

There has been great work on multi-agent learning in the past decade,
but significant challenges remain, including the difficulty of
learning an optimal model/policy from a partial signal, the
exploration vs. exploitation dilemma, the scalability and
effectiveness of learning algorithms, avoiding social dilemmas,
learning emergent communication, learning to cooperate/compete in
non-stationary environments with distributed simultaneously learning
agents, and convergence guarantees.

We are interested in various forms of multi-agent learning for this
symposium, including:
Learning in sequential settings in dynamic environments (such as
stochastic games, decentralized POMDPs and their variants)
Learning with partial observability
Dynamics of multiple learners using (evolutionary) game theory
Learning with various communication limitations
Learning in ad-hoc teamwork scenarios
Scalability through swarms vs. intelligent agents
Bayesian nonparametric methods for multi-agent learning
Deep learning and reinforcement learning methods for multi-agent learning
Transfer learning in multi-agent settings
Applications of multi-agent learning

The purpose of this symposium is to bring together researchers from
machine learning, control, neuroscience, robotics, and multi-agent
communities with the goal of broadening the scope of multi-agent
learning research and addressing the fundamental issues that hinder
the applicability of multi-agent learning for complex real world
problems. This symposium will present a mix of invited sessions,
contributed talks and a poster session with leading experts and active
researchers from relevant fields. Furthermore, the symposium is
designed to allow plenty of time for discussions and initiating
collaborations.

Authors can submit papers of 2-6 pages that will be reviewed by the
organization committee. The papers can present new work or a summary
of recent work. Submissions will be handled through easychair:
https://easychair.org/conferences/?conf=malic18

Organizing Committee:

Christopher Amato, Northeastern University
Thore Graepel, Google DeepMind
Joel Leibo, Google DeepMind
Frans Oliehoek, University of Liverpool
Karl Tuyls, Google DeepMind and University of Liverpool

Invited Speakers:

Sabine Hauert, University of Bristol, Bristol Robotics Lab, UK
Mykel Kochenderfer, Stanford University, US
Ann Nowe, Vrije Universiteit Brussel, Belgium
Peter Stone, University of Texas at Austin, US
Igor Mordatch, OpenAI, US
Nora Ayanian, USC, US
___
uai mailing list
uai@ENGR.ORST.EDU
https://secure.engr.oregonstate.edu/mailman/listinfo/uai

Re: [UAI] CfP: Learning, Inference, and Control of Multi-Agent Systems (MALIC)

[Frans Oliehoek]

Apologies, the correct URL is:
https://sites.google.com/view/malicaaai2018




On Thu, Sep 21, 2017 at 1:27 PM, Frans Oliehoek 
wrote:

> (apologies for cross-posting)
>
> CfP: Learning, Inference, and Control of Multi-Agent Systems 
> (MALIC)https://sites.google.com/site/malicaaai2018/
>
> Description:
>
> We live in a multi-agent world. To be successful in that world, intelligent 
> agents need to learn to consider the agency of others. They will compete in 
> marketplaces, cooperate in teams, communicate with others, coordinate their 
> plans, and negotiate outcomes. Examples include self-driving cars interacting 
> in traffic, personal assistants acting on behalf of humans and negotiating 
> with other agents, swarms of unmanned aerial vehicles, financial trading 
> systems, robotic teams, and household robots.
>
> There has been great work on multi-agent learning in the past decade, but 
> significant challenges remain, including the difficulty of learning an 
> optimal model/policy from a partial signal, the exploration vs. exploitation 
> dilemma, the scalability and effectiveness of learning algorithms, avoiding 
> social dilemmas, learning emergent communication, learning to 
> cooperate/compete in non-stationary environments with distributed 
> simultaneously learning agents, and convergence guarantees.
>
> We are interested in various forms of multi-agent learning for this 
> symposium, including:
> Learning in sequential settings in dynamic environments (such as stochastic 
> games, decentralized POMDPs and their variants)
> Learning with partial observability
> Dynamics of multiple learners using (evolutionary) game theory
> Learning with various communication limitations
> Learning in ad-hoc teamwork scenarios
> Scalability through swarms vs. intelligent agents
> Bayesian nonparametric methods for multi-agent learning
> Deep learning and reinforcement learning methods for multi-agent learning
> Transfer learning in multi-agent settings
> Applications of multi-agent learning
>
> The purpose of this symposium is to bring together researchers from machine 
> learning, control, neuroscience, robotics, and multi-agent communities with 
> the goal of broadening the scope of multi-agent learning research and 
> addressing the fundamental issues that hinder the applicability of 
> multi-agent learning for complex real world problems. This symposium will 
> present a mix of invited sessions, contributed talks and a poster session 
> with leading experts and active researchers from relevant fields. 
> Furthermore, the symposium is designed to allow plenty of time for 
> discussions and initiating collaborations.
>
> Authors can submit papers of 2-6 pages that will be reviewed by the 
> organization committee. The papers can present new work or a summary of 
> recent work. Submissions will be handled through easychair: 
> https://easychair.org/conferences/?conf=malic18
>
> Organizing Committee:
>
> Christopher Amato, Northeastern University
> Thore Graepel, Google DeepMind
> Joel Leibo, Google DeepMind
> Frans Oliehoek, University of Liverpool
> Karl Tuyls, Google DeepMind and University of Liverpool
>
> Invited Speakers:
>
> Sabine Hauert, University of Bristol, Bristol Robotics Lab, UK
> Mykel Kochenderfer, Stanford University, US
> Ann Nowe, Vrije Universiteit Brussel, Belgium
> Peter Stone, University of Texas at Austin, US
> Igor Mordatch, OpenAI, US
> Nora Ayanian, USC, US
>
>
___
uai mailing list
uai@ENGR.ORST.EDU
https://secure.engr.oregonstate.edu/mailman/listinfo/uai

[UAI] PhD position in planning under uncertainty / RL

[Frans Oliehoek]

(apologies for cross posting)

Dear colleagues and students,

I am pleased to announce that, Prof. Von-Wun Soo and myself can offer a
PhD position in the context of the 4-year dual PhD programme at National
Tsing Hua University (NTHU) and the University of Liverpool.

Topic: Improvements of Monte Carlo Tree Search for Real Applications
Deadline: 31st of May 2017
URL:
https://www.findaphd.com/search/ProjectDetails.aspx?PJID=84967&LID=2184

Description:

In recent years techniques of sequential decision making have taken a
flight. Many of the recent advances are based on simulation-based
planning and, in particular, so-called Monte Carlo Tree Search (MCTS)
methods [2,3]. These methods are very flexible and in the limit they
will converge to the optimal policy that takes into account execution
uncertainty (e.g., stochastic outcome of actions) in a principled
fashion. However, despite these attractive features, there are some
domain properties that are challenging for MCTS. The goal of this
project is to explore advances in MCTS that address these difficulties
in the context of applications such as nano-grids and multi-robot teams.

This project is a part of a 4-year dual PhD programme between National
Tsing Hua University (NTHU) in Taiwan and the University of Liverpool in
UK. It is planned that students will spend time studying in each
institution.  Both the University of Liverpool and NTHU have agreed to
waive the tuition fees for the duration of the project. Moreover, a
stipend of TWD 10,000/month will be provided to cover part of the living
costs.


I would be grateful if you could forward this message to suitable
candidates.

Best regards,
-Frans Oliehoek



p.s.: As a reminder, I am also recruiting for a different position:

Topic: Deep learning for Multi-agent Reinforcement Learning and Decision
Making
Deadline: Monday, April 3 2017
https://www.findaphd.com/search/ProjectDetails.aspx?PJID=83836&LID=2184%29



___
uai mailing list
uai@ENGR.ORST.EDU
https://secure.engr.oregonstate.edu/mailman/listinfo/uai

[UAI] PhD position deep multiagent RL at Liverpool

[Frans Oliehoek]

(apologies for cross posting)

Dear colleagues and students,

The Department of Computer Science at the University of Liverpool is
pleased to offer a funded PhD position:

Topic: Deep learning for Multi-agent Reinforcement Learning and Decision
Making
Deadline: Monday, April 3 2017
URL:
https://www.findaphd.com/search/ProjectDetails.aspx?PJID=83836&LID=2184%29

Description:
Multi-agent Sequential Decision Making lies in the intersection of
multiagent systems (MASs), reinforcement learning and
(decision-theoretic) planning. It studies how agents can take
intelligent decisions to optimize their long term goals in the presence
of multiple intelligent decision makers.

In this project, we will investigate novel ways by which (deep) machine
learning techniques can be used to improve the coordination of such
MASs. The developed techniques will be analyzed and evaluated in
simulation in different application domains such as traffic light
control [8] and robotics simulators [2]. There is also the opportunity
to apply the techniques to teams of real robots using a subset of the
smARTlab’s 30 Turtlebots.

I would be grateful if you could forward this message to suitable
candidates.

Best regards,
-Frans Oliehoek


___
uai mailing list
uai@ENGR.ORST.EDU
https://secure.engr.oregonstate.edu/mailman/listinfo/uai

[UAI] PhD Positions at the University of Liverpool

[Frans Oliehoek]

(apologies for cross-posting)


PhD Positions at the University of Liverpool

The Department of Computer Science of the University of Liverpool offers
a number of PhD positions in the research fields pursued in the
department. We have four positions available for home and EU students in
EEECS for starting in 2017.

Our research is centred around the following themes:

agent logics
algorithmic game theory
algorithms and data structures
approximation algorithms
argumentation and dialogue
auctions and mechanism design
automata and game theory
automated reasoning
autonomous agents
bioinformatics, computational biology and medicine
coalition games
computational complexity and computability theory
computational economics
control theory
data mining
database theory
deep learning
distributed and parallel computing
equilibrium computation
graph algorithms
judgement aggregation
machine learning
Markov chains and decision processes
multi agent systems
natural language processing
network and congestion games
network communication
ontologies
randomised algorithms and data structures
reinforcement learning
robotics
scheduling and energy optimisation
synthesis
stochastic games
temporal logics
voting theory

To learn more about our exciting research environment, staff, and
students, we encourage you to study the pages of our research groups on
Algorithms and Optimisation
https://intranet.csc.liv.ac.uk/research/optimisation/
,
Argumentation https://intranet.csc.liv.ac.uk/research/argumentation/
,
Automata, Computability and Complexity Theory
https://intranet.csc.liv.ac.uk/research/complexity/
,
Data Mining and Machine Learning
https://intranet.csc.liv.ac.uk/research/dmml/
,
Economics and Computation https://intranet.csc.liv.ac.uk/research/ecco/
,
Knowledge Representation https://intranet.csc.liv.ac.uk/research/kr/
,
Networks and Distributed Computing
https://intranet.csc.liv.ac.uk/research/networks/
,
Robotics and Autonomous Systems
https://intranet.csc.liv.ac.uk/research/robotics/
, and
Verification https://intranet.csc.liv.ac.uk/research/verification/
,
and to contact prospective supervisors to discuss a research topic
before you apply.

You can apply through http://www.liv.ac.uk/study/postgraduate/applying/
.

The deadline for this application round is Friday, December 2nd. While
applications will be possible until all positions are filled, your
chances will be increased by applying before this deadline.

Please do not hesitate to ask (sven.sch...@liverpool.ac.uk or
eeecs...@liverpool.ac.uk) if you have any questions.

Dr. Sven Schewe
PhD Admission Officer
Department of Computer Science
University of Liverpool
http://www.csc.liv.ac.uk/~sven/
(+44 151) 79 54242
sven.sch...@liverpool.ac.uk

___
uai mailing list
uai@ENGR.ORST.EDU
https://secure.engr.oregonstate.edu/mailman/listinfo/uai

[UAI] Sequential Decision Making for Intelligent Agents (SDMIA)

[Frans Oliehoek]

=
Call for Participation:

Sequential Decision Making for Intelligent Agents (SDMIA)
AAAI Fall Symposium
http://masplan.org/sdmia

Dates: November 12–14, 2015
Location: Arlington, Virginia adjacent to Washington, DC

Registration is open (deadline Oct 16):
https://www.regonline.com/fss15
=

Sequential decision making under uncertainty (SDM) is a powerful
paradigm for probabilistic planning. The emergence of various models
that analyze it under different sets of assumptions, e.g., as single-
and multi-agent MDPs and POMDPs, has gone hand in hand with the split of
this field into many subareas,  each with a quite distinct research
community. The SDMIA Fall Symposium aims to bring the researchers of
computational sequential decision making under uncertainty together, in
order to facilitate the cross-pollination of ideas across these
communities and thus accelerate the development of the larger field. The
symposium will have ample room for discussions and interaction.
Furthermore, we intend to reflect on the current state of the field,
both in terms of theory and applications, and, more importantly, ways to
shape its future.

Program

We have received submissions on a great variety of topics within SDM,
including:

-applications of SDM
-advances in planning approaches and reinforcement learning
-GPU accelerated computation
-software for SDM

The full list of accepted papers can be found here:
http://masplan.org/sdmia_accepted_papers


Invited speakers:

Craig Boutilier, Google
Emma Brunskill, CMU
Alan Fern, Oregon State
Mykel Kochenderfer, Stanford
Milind Tambe, USC
Jason Williams, Microsoft Research
Shlomo Zilberstein, UMass Amherst

For titles and abstracts, please see:
http://masplan.org/sdmia_invited_speakers


Organizing Committee

Matthijs Spaan (chair), Delft University of Technology,

Frans Oliehoek, University of Amsterdam / University of Liverpool,

Christopher Amato, University of New Hampshire, 
Andrey Kolobov, Microsoft Research, 
Pascal Poupart, University of Waterloo, 

We happily answer any questions about the symposium.

___
uai mailing list
uai@ENGR.ORST.EDU
https://secure.engr.oregonstate.edu/mailman/listinfo/uai

[UAI] PhD position at the University of Liverpool

[Frans Oliehoek]

The Department of Computer Science of the University of Liverpool offers
a PhD position in the research fields pursued in the department. The
position is available for home and EU students in Computer Science
starting in late 2015 or early 2016.

Our research is centred around the following themes:

algorithmic game theory
algorithmic mechanism design
algorithms and data structures
approximation algorithms
agent logics
argumentation and dialogue
automata and game theory
automated reasoning
autonomous agents
bioinformatics, computational biology and medicine
complexity of equilibria
computational complexity and computability theory
computational economics
control theory
data mining
database theory
distributed and parallel computing
graph algorithms
machine learning
Markov chains and decision processes
multi agent systems
natural language processing
network and congestion games
network communication
ontologies
randomised algorithms and data structures
robotics
scheduling and energy optimisation
synthesis
temporal logics

To learn more about our exciting research environment, staff, and
students, we encourage you to study the pages of our research groups on

Agents: http://www.csc.liv.ac.uk/research/agents/,
Complexity Theory and Algorithms:
http://www.csc.liv.ac.uk/research/ctag/,
Economics and Computation: http://www.csc.liv.ac.uk/research/ecco/, and
Logic and Computation: http://www.csc.liv.ac.uk/research/logics/

and to contact prospective supervisors to discuss a research topic
before you apply.

You can apply through http://www.liv.ac.uk/study/postgraduate/applying/.

The deadline for this application round is Monday, September 7, 2015.
While applications will be possible until the position is filled, your
chances will be increased by applying before this deadline.

Please do not hesitate to ask (sven.sch...@liverpool.ac.uk or
hann...@liverpool.ac.uk) if you have any questions.
___
uai mailing list
uai@ENGR.ORST.EDU
https://secure.engr.oregonstate.edu/mailman/listinfo/uai

[UAI] CfP: Sequential Decision Making for Intelligent Agents *extended deadline*

[Frans Oliehoek]

=== CfP: Sequential Decision Making for Intelligent Agents ===

AAAI Fall Symposium
November 12–14, 2015
Arlington, Virginia
http://masplan.org/sdmia

*Extended* submission deadline: July 22, 2015

Sequential decision making under uncertainty (SDM) is a powerful
paradigm for probabilistic planning. The emergence of various models
that analyze SDM under different sets of assumptions, e.g., as single-
and multi-agent Markov Decision Processes (MDPs) and Partially
Observable MDPs (POMDPs), has gone hand in hand with the split of this
field into many subareas, each with a quite distinct research community.
The Sequential Decision Making for Intelligent Agents (SDMIA) Fall
Symposium aims to bring the researchers of computational sequential
decision making under uncertainty together, in order to facilitate the
cross-pollination of ideas across these communities and thus accelerate
the development of the larger field. The symposium will have ample time
for discussions and interaction. Furthermore, we intend to reflect on
the current state of the field, both in terms of theory and
applications, and, more importantly, ways to shape its future.

We invite submissions, both original as well as previously published,
dealing with the general topic of sequential decision making under
uncertainty. Topics of particular interest include, but are not limited to:
- Novel insights in modeling sequential decision making (SDM)
- Recent advances in solution methods
- Benchmark problems and benchmarking
- Real-world applications and application domains
- Model specification and induction
- Methods for transferring solutions from one model to another

We particularly encourage contributions that have the potential to make
an impact on different sub-fields of SDM, but this is not a requirement.
Submission instructions can be found on our website:
http://masplan.org/sdmia

Organizing Committee

Matthijs Spaan (chair), Delft University of Technology
Frans Oliehoek, University of Amsterdam / University of Liverpool
Christopher Amato, University of New Hampshire
Andrey Kolobov, Microsoft Research
Pascal Poupart, University of Waterloo

___
uai mailing list
uai@ENGR.ORST.EDU
https://secure.engr.oregonstate.edu/mailman/listinfo/uai

[UAI] CfP: Sequential Decision Making for Intelligent Agents

[Frans Oliehoek]

=== CfP: Sequential Decision Making for Intelligent Agents ===

AAAI Fall Symposium
November 12–14, 2015
Arlington, Virginia
http://masplan.org/sdmia

Submission deadline: July 15, 2015

Sequential decision making under uncertainty (SDM) is a powerful
paradigm for probabilistic planning. The emergence of various models
that analyze SDM under different sets of assumptions, e.g., as single-
and multi-agent Markov Decision Processes (MDPs) and Partially
Observable MDPs (POMDPs), has gone hand in hand with the split of this
field into many subareas, each with a quite distinct research community.
The Sequential Decision Making for Intelligent Agents (SDMIA) Fall
Symposium aims to bring the researchers of computational sequential
decision making under uncertainty together, in order to facilitate the
cross-pollination of ideas across these communities and thus accelerate
the development of the larger field. The symposium will have ample time
for discussions and interaction. Furthermore, we intend to reflect on
the current state of the field, both in terms of theory and
applications, and, more importantly, ways to shape its future.

We invite submissions, both original as well as previously published,
dealing with the general topic of sequential decision making under
uncertainty. Topics of particular interest include, but are not limited to:
- Novel insights in modeling sequential decision making (SDM)
- Recent advances in solution methods
- Benchmark problems and benchmarking
- Real-world applications and application domains
- Model specification and induction
- Methods for transferring solutions from one model to another

We particularly encourage contributions that have the potential to make
an impact on different sub-fields of SDM, but this is not a requirement.
Submission instructions can be found on our website:
http://masplan.org/sdmia

Organizing Committee

Matthijs Spaan (chair), Delft University of Technology
Frans Oliehoek, University of Amsterdam / University of Liverpool
Christopher Amato, University of New Hampshire
Andrey Kolobov, Microsoft Research
Pascal Poupart, University of Waterloo

___
uai mailing list
uai@ENGR.ORST.EDU
https://secure.engr.oregonstate.edu/mailman/listinfo/uai

[UAI] MSDM 2011: 2nd CFP / deadline extended

[Frans Oliehoek]

-Apologies for multiple copies of this announcement-


Dear colleague,

The deadline for MSDM 2011 has been extended. The updated CFP can be 
found below. Please forward it to anyone who might be interested.


With kind regards,
Frans Oliehoek






=
CALL FOR PAPERS
AAMAS 2011 Workshop
Multiagent Sequential Decision-Making in Uncertain Domains (MSDM)
=

Sixth Workshop in the MSDM series
May 3, 2010
Taipei, Taiwan
http://teamcore.usc.edu/junyounk/msdm2011/

In sequential decision making, an agent's objective is to choose 
actions, based on its observations of the world, that will maximize its 
performance over the course of a series of such decisions. In worlds 
where action consequences are nondeterministic or observations 
incomplete, Markov Decision Processes (MDPs) and Partially-Observable 
MDPs (POMDPs) serve as the basis for principled approaches to 
single-agent sequential decision making. Extending these models to 
systems of multiple agents has become the subject of an increasingly 
active area of research over the past decade and a variety of different 
multiagent models have emerged (e.g., the MMDP, Dec-POMDP, MTDP, 
I-POMDP, and POSG). The high computational complexity of these models 
has also driven researchers to develop multiagent planning and learning 
methods that exploit structure in agents' interactions, methods geared 
towards efficient approximate solutions, and decentralized methods that 
distribute computation among the agents.


The primary purpose of this workshop is to bring together researchers in 
the field of MSDM to present and discuss new work, to identify recent 
trends in model and algorithmic development, and to establish important 
directions and goals for further research and collaboration. A secondary 
goal is to help address an important challenge; in order to make the 
field more accessible to newcomers, and to facilitate multidisciplinary 
collaboration, we seek to bring order in the large number of models and 
methods that have been introduced over the last decade. The workshop 
also aims to discuss interesting and challenging application areas 
(e.g., cooperative robotics, distributed sensor and/or communication 
networks, decision support systems) and suitable evaluation methodologies.



Topics
--
Multiagent sequential decision making comprises (1) problem 
representation, (2) planning, (3) coordination, and (4) learning during 
execution. The MSDM workshop addresses this full range of aspects. 
Topics of particular interest include:


- Novel representations, algorithms and complexity results.
- Comparisons of algorithms.
- Relationships between models and their assumptions.
- Decentralized vs. centralized planning approaches.
- Online vs. offline planning.
- Communication and coordination during execution.
- Dealing with...
...large numbers of agents.
...large numbers of / continuous states, observations and actions.
...long decision horizons.
- (Reinforcement) learning in partially observable multiagent systems.
- Cooperative, competitive, and self-interested agents.
- Application domains.
- Benchmarks and evaluation methodologies.
- Standardization of software.
- Past trends and future directions of MSDM research.
- High-level principles in MDSM.


Important Dates

January 31, 2011 - Submission deadline
February 27, 2011 - Notification of Acceptance
May 3, 2011 - Workshop


Submission instructions
---
Authors are encouraged to submit papers up to 8 pages in length in the 
AAMAS2011 format. Submissions should be uploaded in PDF form at 
http://www.easychair.org/conferences/?conf=msdm2011. Each submission 
will be reviewed by at least two Program Committee members. The review 
process will be "single-blind"; thus authors do not have to remove their 
names when submitting papers.



Organizing Committee

Prashant Doshi University of Georgia
Abdel-Illah Mouaddib University of Caen Basse-Normandie
Stefan Witwicki University of Michigan
Jun-young Kwak University of Southern California
Frans A. Oliehoek MIT

Program Committee
-
Martin Allen University of Wisconsin - La Crosse
Christopher Amato Aptima, Inc.
Aurelie Beynier University Pierre and Marie Curie (Paris 6)
Brahim Chaib-draa Laval University
Georgios Chalkiadakis University of Southampton
Alessandro Farinelli University of Verona
Piotr Gmytrasiewicz University of Illinois Chicago
Rajiv Maheswaran University of Southern California
Francisco S. Melo INESC-ID Lisboa
Hala Mostafa University of Massachussetts, Amherst
Enrique Munoz de Cote University of Southampton
Brenda Ng Lawrence Livermore National Laboratory
Simon Parsons Brooklyn College
David Pynadath Institute for Creative Technologies, USC
Xia Qu University of Georgia
Zinovi Rabinovich University of Southampton
Paul Scerri Carneg

[UAI] CFP: MSDM 2011 - Multi-agent Sequential Decision-Making in Uncertain Domains

[Frans Oliehoek]

==
  CALL FOR PAPERS
AAMAS 2011 Workshop
Multi-agent Sequential Decision-Making in Uncertain Domains (MSDM)
==

Sixth Workshop in the MSDM series
May 2 or 3, 2010
Taipei, Taiwan
http://teamcore.usc.edu/junyounk/msdm2011/

In sequential decision making, an agent's objective is to choose 
actions, based on its observations of the world, that will maximize its 
performance over the course of a series of such decisions. In worlds 
where action consequences are nondeterministic or observations 
incomplete, Markov Decision Processes (MDPs) and Partially-Observable 
MDPs (POMDPs) serve as the basis for principled approaches to 
single-agent sequential decision making. Extending these models to 
systems of multiple agents has become the subject of an increasingly 
active area of research over the past decade and a variety of different 
multiagent models have emerged (e.g., the MMDP, Dec-POMDP, MTDP, 
I-POMDP, and POSG).  The high computational complexity of these models 
has also driven researchers to develop multiagent planning and learning 
methods that exploit structure in agents' interactions, methods geared 
towards efficient approximate solutions, and decentralized methods that 
distribute computation among the agents.



The primary purpose of this workshop is to bring together researchers in 
the field of MSDM to present and discuss new work, to identify recent 
trends in model and algorithmic development, and to establish important 
directions and goals for further research and collaboration. A secondary 
goal is to help address an important challenge; in order to
make the field more accessible to newcomers, and to facilitate 
multidisciplinary collaboration, we seek to bring order in the large 
number of models and methods that have been introduced over the last 
decade.  The workshop also aims to discuss interesting and challenging 
application areas (e.g., cooperative robotics, distributed sensor and/or 
communication networks, decision support systems) and suitable 
evaluation methodologies.



Topics
--
Multiagent sequential decision making comprises (1) problem 
representation, (2) planning, (3) coordination, and (4) learning during 
execution. The MSDM workshop addresses this full range of aspects. 
Topics of particular interest include:


- Novel representations, algorithms and complexity results.
- Comparisons of algorithms.
- Relationships between models and their assumptions.
- Decentralized vs. centralized planning approaches.
- Online vs. offline planning.
- Communication and coordination during execution.
- Dealing with...
   ...large numbers of agents.
   ...large numbers of / continuous states, observations and actions.
   ...long decision horizons.
- (Reinforcement) learning in partially observable multiagent systems.
- Cooperative, competitive, and self-interested agents.
- Application domains.
- Benchmarks and evaluation methodologies.
- Standardization of software.
- Past trends and future directions of MSDM research.
- High-level principles in MDSM.


Important Dates

January 30, 2011  - Submission deadline (strict)
February 27, 2011 - Notification of Acceptance
May 2, 2011   - Workshop


Submission instructions
---
Authors are encouraged to submit papers up to 8 pages in length in the 
AAMAS2011 format. Submissions should be uploaded in PDF form at 
http://www.easychair.org/conferences/?conf=msdm2011. Each submission 
will be reviewed by at least two Program Committee members. The review 
process will be "single-blind"; thus authors do not have to remove their 
names when submitting papers.



Organizing Committee


Prashant DoshiUniversity of Georgia
Abdel-Illah Mouaddib  University of Caen Basse-Normandie
Stefan Witwicki   University of Michigan
Jun-young KwakUniversity of Southern California
Frans A. Oliehoek MIT

Program Committee
-
Martin Allen  University of Wisconsin - La Crosse
Christopher Amato Aptima, Inc.
Aurelie Beynier   University Pierre and Marie Curie (Paris 6)
Brahim Chaib-draa Laval University
Georgios Chalkiadakis University of Southampton
Alessandro Farinelli  University of Verona
Piotr Gmytrasiewicz   University of Illinois Chicago
Rajiv Maheswaran  University of Southern California
Francisco S. Melo INESC-ID Lisboa
Hala Mostafa  University of Massachussetts, Amherst
Enrique Munoz de Cote University of Southampton
Brenda Ng Lawrence Livermore National Laboratory
Simon Parsons Brooklyn College
David PynadathInstitute for Creative Technologies, USC
Xia QuUniversity of Georgia
Zinovi Rabinovich University of Southampton
Paul Scerri   Carnegie Mellon University
Matthijs SpaanInstitute for Systems and