[UAI] Call for Papers: Special Issue on Autonomous Agents Modelling Other Agents
*Special Issue on Autonomous Agents Modelling Other Agents* To be published in Artificial Intelligence https://www.journals.elsevier.com/artificial-intelligence/call-for-papers/special-issue-on-autonomous-agents-modelling-other-agents Dear Colleagues, We invite you to contribute to a new special issue on the topic of Autonomous Agents Modelling Other Agents, to be published in the journal Artificial Intelligence. Much research in artificial intelligence (AI) is concerned with enabling autonomous agents to model various aspects of other agents, such as their beliefs, intentions, plans, goals, and decision making. A recent survey published in AIJ (https://doi.org/10.1016/j.artint.2018.01.002) discusses the major modelling methods that have been developed in AI research and highlights open problems. The survey shows that this is a large area of research with a history going back several decades. However, it also shows that the area is fractured into many sub-communities with little interaction, including work in game playing, computer poker, automated negotiation, simulated robot soccer, human user modelling, human-robot interaction, commercial video games, trust and reputation, and multi-agent learning. The purpose of this special issue is to provide a venue for new technical contributions addressing open problems in this area (including those highlighted in the survey), as well as to ! complement the survey via research perspectives which may include historical accounts, a description of recent developments and applications, and personal views about current limitations and future directions. The following is a non-exclusive list of topics relevant to the special issue: Learning and using models of other agents' decision making processes Opponent modelling in games Methods for goal/intent/plan recognition Theory of mind, recursive reasoning, epistemic planning Implicit agent modelling Modelling humans Modelling other agents under partial observability Modelling teams/groups of agents Teammate modelling for ad hoc teamwork Robust decision making with agent models Reasoning about utilities and preferences of other agents Modelling other agents in open multi-agent systems Modelling changing behaviours of other agents Safe exploration of agent model spaces Misspecified agent models and model revision Graphical representations of agent models Innovative applications of agents modelling other agents Historical accounts, current limitations, and future directions of agent modelling Submissions will be open from June 2018 until December 31, 2018 and can be made using the EVISE system: http://www.evise.com/evise/faces/pages/navigation/NavController.jspx?JRNL_ACR=ARTINT. Authors should select when they reach the âArticle Typeâ step in the submission process. All submitted articles will go through a peer-review process. Reviewing of submitted articles begins immediately after submission, with first decisions (accept, reject, revisions) made within three months. Accepted articles will be published immediately online on the AIJ website and will also be included in the special issue. Guest editors: Stefano Albrecht University of Edinburgh Peter Stone University of Texas at Austin Michael Wellman University of Michigan -- The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336. ___ uai mailing list uai@ENGR.ORST.EDU https://secure.engr.oregonstate.edu/mailman/listinfo/uai
[UAI] Call for Papers: Special Issue on Autonomous Agents Modelling Other Agents
Special Issue on Autonomous Agents Modelling Other Agents Published in Artificial Intelligence Call for Papers: https://www.journals.elsevier.com/artificial-intelligence/call-for-papers/special-issue-on-autonomous-agents-modelling-other-agents Dear Colleagues, We invite you to contribute to a new special issue on the topic of Autonomous Agents Modelling Other Agents, to be published in the journal Artificial Intelligence. Much research in artificial intelligence (AI) is concerned with enabling autonomous agents to model various aspects of other agents, such as their beliefs, intentions, plans, goals, and decision making. A recent survey on the topic, published in AIJ (https://doi.org/10.1016/j.artint.2018.01.002), discusses the major modelling methods that have been developed in AI research and highlights open problems. The survey shows that this is a large area of research with a history going back several decades. However, it also shows that the area is fractured into many sub-communities with little interaction, including work in game playing, computer poker, automated negotiation, simulated robot soccer, human user modelling, human-robot interaction, commercial video games, trust and reputation, and multi-agent learning. The purpose of this special issue is to provide a venue for new technical contributions addressing open problems in this area of research (including those highlighted in ! the survey), as well as to complement the survey via research perspectives which may include historical accounts, a description of recent developments and applications, and personal views about current limitations and future directions. The following is a non-exclusive list of topics relevant to the special issue: Learning and using models of other agents' decision making processes Opponent modelling in games Methods for goal/intent/plan recognition Theory of mind, recursive reasoning, epistemic planning Implicit agent modelling Modelling humans Modelling other agents under partial observability Modelling teams/groups of agents Teammate modelling for ad hoc teamwork Robust decision making with agent models Reasoning about utilities and preferences of other agents Modelling other agents in open multi-agent systems Modelling changing behaviours of other agents Safe exploration of agent model spaces Misspecified agent models and model revision Graphical representations of agent models Innovative applications of agents modelling other agents Historical accounts, current limitations, and future directions of agent modelling Submissions can be made until December 31, 2018 using the EVISE system: http://www.evise.com/evise/faces/pages/navigation/NavController.jspx?JRNL_ACR=ARTINT. Authors should select when they reach the âArticle Typeâ step in the submission process. All submitted articles will go through a peer-review process. Reviewing of submitted articles begins immediately after submission, with first decisions (accept, reject, revisions) made within three months. Accepted articles will be published immediately online on the AIJ website and will also be included in the special issue. Guest editors: Stefano Albrecht, University of Edinburgh Peter Stone, University of Texas at Austin Michael Wellman, University of Michigan -- The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336. ___ uai mailing list uai@ENGR.ORST.EDU https://secure.engr.oregonstate.edu/mailman/listinfo/uai
[UAI] Call for Tutorials: AAMAS 2019
*** Call for Tutorials AAMAS 2019: May 13-17, 2019 in Montreal, Canada WWW: http://aamas2019.encs.concordia.ca/ *** The AAMAS 2019 Organizing Committee invites proposals for the Tutorial Program to be held on May 13-14th 2019, immediately before the technical conference. AAMAS 2019 Tutorials should serve one or more of the following objectives: * Introduce novices to major topics of AAMAS research. * Provide instruction in established practices and methodologies. * Survey a mature area of AAMAS research or practice. * Motivate and explain an AAMAS topic of emerging importance. * Introduce expert non-specialists to an AAMAS area. * Survey an area of agent research especially relevant for people from industry. * Present a novel synthesis combining distinct lines of AAMAS work. * Introduce AAMAS audiences to an external topic that can motivate or use AAMAS research. Topic areas of interest include all of those listed in the call for the technical track (see http://aamas2019.encs.concordia.ca/), including the special tracks. Tutorials will be half day long. A few full day tutorials may be accepted, but the proponents need to motivate their request when submitting their proposal. SUBMISSION REQUIREMENTS Those interested in presenting a tutorial should email their proposal to one of the tutorial chairs (see below). Proposals should be two to four pages in length, formatted using the AAMAS paper template, and should contain the following information: 1. A short title of the tutorial. 2. A brief description of the tutorial, suitable for inclusion in the conference registration brochure. 3. A detailed outline of the tutorial, including preferred length (half or full day). 4. Characterization of the potential target audience for the tutorial, including prerequisite knowledge. 5. A description of why the tutorial topic would be of interest to a substantial part of the AAMAS audience. 6. A brief resume of the presenter(s), which should include name, postal address, phone (and fax) numbers, email address, background in the tutorial area, any available example of work in the area (ideally, a published tutorial-level article on the subject), evidence of teaching experience (including references that address the proposer's presentation skills as applicable), and evidence of scholarship in the area. Information about previous tutorials delivered by the presenters (if any). 7. The name and e-mail address of the corresponding presenter. The corresponding presenter should be available for e-mail correspondence during the evaluation process, in the case clarifications and discussions on the scope and content of the proposal are needed. The evaluation of the proposal will take into account the level of general interest for AAMAS attendees, the quality of the proposal, and the expertise and skills of the presenters. We emphasize that the primary criteria for evaluation will be whether a proposal is interesting, well-structured, and motivated, rather than the perceived experience/standing of the proposer. Those submitting a proposal should keep in mind that tutorials are intended to provide an overview of the field; they should present reasonably well established information in a balanced way. Tutorials should not be used to advocate a single avenue of research, nor should they promote a product. The selection of the tutorials to be included in the final AAMAS program will be based upon a number of factors, including: the scientific/technical interest of the topics, the quality of the proposal, the need to avoid strictly overlapping tutorials, and the unavoidable need to limit the overall number of selected tutorials. RESPONSIBILITIES (with respect to accepted proposals) AAMAS will be responsible for: * Providing logistic support and a meeting place for the tutorial. * Together with the organizers, determining the tutorial date and time. * Advertising the availability of the tutorial material to the AAMAS 2019 participants. Tutorial organizers will be responsible for: * Providing AAMAS with a legible PDF copy of their tutorial notes by May 6th, 2019. * Providing a web site for the tutorial, which will include title and abstract of the tutorial, presenters' details, outline, tutorial notes and related reading material. The Tutorial co-chairs will ask the Tutorial organizers to follow some common format and style for their web sites, in order to make them as homogeneous as possible. More details will be provided upon acceptance. * Presenting the tutorial at AAMAS 2019. AAMAS reserves the right to cancel any tutorial if the above responsibilities are not fulfilled, if deadlines are missed, or if too few attendees register for the tutorial to support the costs of running the tutorial. IMPORTANT DATES November 30,
