[agents] CfP: JAAMAS Special Issue on “New Horizons in Multiagent Learning”

[Matt Taylor]

Dear Colleagues,

It is our pleasure to invite you to submit your research papers to the
Special Issue on “New Horizons in Multiagent Learning” in the journal of
Autonomous Agents and Multi-Agent Systems.



https://static.springer.com/sgw/documents/1644414/application/pdf/AGNT+-+CFP+-+New+Horizons+in+Multiagent+Learning.pdf



--------


Learning is a critical component for autonomous agents so that they can
discover novel behaviors, adapt to a non-stationary world, and handle
unanticipated events. As virtual and physical agents become more common,
these learning agents need to handle interactions not only with an
environment, but also with other agents. Multiagent learning thus becomes
an indispensable component of building intelligent systems, even though
much of the current learning research focuses on single-agent settings.

Recent breakthroughs in deep learning have energized both academic and
industrial research labs, allowing new types and difficulties of complex
tasks to be successfully learned. Some recent work has also shown the great
promise of applying deep reinforcement learning techniques in multi-agent
settings, incentivizing the further exploration of this avenue and the
development of new deep learning multiagent architectures. This line of
research is particularly important because there are many new problems that
can be explored and tackled by deep multiagent learning, from both
empirical and theoretical perspectives.

This special issue aims to gather novel research articles, overview
articles, and position papers to highlight the recent interest and advances
in multi-agent learning. For the latter two types of papers, contacting the
guest editors prior to submission is highly encouraged. For research
articles, relevant topics include, but are not limited to, the following:

* Learning in Markov games, imperfect information games
* Swarm intelligence/learning
* Evolutionary methods
* Emergent behaviors
* Learning in the presence of other strategic agents
* Opponent modeling
* Learning to communicate
* Mechanism design for learning agents
* Inter-agent teaching and transfer
* Speedup methods for multi-agent learning
* Learning for heterogeneous multi-agent systems
* Learning in multi-robot systems
* Combining multiagent learning with other areas (e.g., search, learning from
demonstrations, etc.)

Issue Editors
Matthew E. Taylor, Borealis AI (matthew.taylor at borealisai.com)
Karl Tuyls, Deepmind & KU Leuven (karltuyls at google.com)

Submissions and Reviews Procedures
Special Issues are handled in the normal way via the online Editorial
Manager system found at https://agnt.edmgr.com. Please choose the article
type “S.I. : New Horizons in Multiagent Learning.” Special Issue articles
should fulfill all the standard requirements of any JAAMAS article. Authors
should note that the same criteria apply to articles in Special Issues as
to regular articles. All papers will undergo the same rigorous AGNT review
process. Please refer to the JAMAAS website for detailed instructions on
paper submission: http://www.springer.com/computer/ai/journal/10458



Submission deadline: March 4, 2019


---------------------------------------------
Matt Taylor
BorealisAI.com
http://eecs.wsu.edu/~taylorm
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.cs.umbc.edu/pipermail/agents/attachments/20181123/d7813de9/attachment.html>