AI 2016 - Special Issue on Multiagent Interaction without Prior Coordination

Interaction between agents is the defining attribute of multiagent systems, encompassing problems of planning in a decentralized setting, learning other agent models, composing teams with high task performance, and selected resource-bounded communication and coordination. There is significant variety in methodologies used to solve such problems, including symbolic reasoning about negotiation and argumentation, distributed optimization methods, machine learning methods such as multiagent reinforcement learning, etc. The majority of these well studied methods depend on some form of prior coordination. Often, the coordination is at the level of problem definition. For example, learning algorithms may assume that all agents share a common learning method or prior beliefs, distributed optimization methods may assume specific structural constraints regarding the partition of state space or cost/rewards, and symbolic methods often make strong assumptions regarding norms and protocols. However, in realistic problems, these assumptions are easily violated ? calling for new models and algorithms that specifically address the case of multiagent interaction without prior coordination. Similar issues are also becoming increasingly more pertinent in human-machine interactions, where there is a need for intelligent adaptive behaviour and assumptions regarding prior knowledge and communication are problematic.
This special issue seeks mature high-quality research related to multiagent interaction without prior coordination. This includes empirical and theoretical investigations of issues arising from assumptions regarding prior coordination in interactive settings, as well as solutions in the form of novel models and algorithms for effective multiagent interaction without prior coordination.
Topics
A non-exclusive list of relevant topics includes:
Agent coordination and cooperation without prior coordination
Learning and adaptation in multiagent systems without prior coordination
Team formation and information sharing in ad hoc teamwork settings
Human-machine interaction without prior coordination
Teammate/opponent modelling and plan recognition without prior coordination
Game theory/incomplete information applied to ad hoc agent coordination
Empirical and theoretical investigations of issues arising from prior assumptions
Ad hoc coordination in the presence of adversaries
Submission Details
Articles can be submitted until December 15, 2015 via EditorialManager. After registering as an author, click on "Submit New Manuscript" and choose "S.I. : Multiagent Interaction without Prior Coordination" as the article type. Articles must follow the formatting guidelines of JAAMAS.
Articles will be selected via a single-blind peer review process, based on novelty, significance, technical quality, and clarity. Please include all author names and affiliations.
Reviewing of articles begins immediately after submission. However, given the limited space of the special issue, we will in most cases have to wait until all submitted articles have been reviewed before a decision can be made. Only in clear accept or reject cases will we send an early notification.
Note that although this special issue is motivated by the AAAI workshop series on MIPC, there is no special treatment for workshop authors.
Guest Editors
Stefano V. Albrecht (ku.ca.de.sms-AT-thcerbla.v.s)
The University of Edinburgh, United Kingdom
Somchaya Liemhetcharat (gs.ude.rats-a.r2i-AT-s-tehmeil)
Institute for Infocomm Research, A*STAR, Singapore
Peter Stone (ude.saxetu.sc-AT-enotsp)
The University of Texas at Austin, USA