The 15th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE-19) is the next in an annual series of conferences showcasing interdisciplinary research on modeling, developing, and evaluating intelligent systems in entertainment. AIIDE-19 provides a meeting place for AI researchers and practitioners to discuss the latest advances and contemporary issues in entertainment-focused AI. The conference has a long-standing history of featuring research on artificial intelligence in computer games, and continues to grow into entertainment areas beyond games. We invite researchers, developers, and digital artists to share ideas on topics at the intersection of all forms of entertainment and artificial intelligence. AIIDE-19 will feature invited speakers, paper sessions, workshops, tutorials, playable experiences, artifact evaluation, panels, posters, AI competitions, a reception, and a doctoral consortium. AIIDE-19 is sponsored by the Association for the Advancement of Artificial Intelligence (AAAI).
|April 19, 2019||Workshop Proposals|
|May 1, 2019||Workshop Notifications|
|May 24, 2019||Abstract Deadline (Research Papers Track Only)|
|May 30, 2019||Papers, Demos, and Playable Experiences Deadline|
|June 13, 2019||Doctoral Consortium Deadline|
|June 28, 2019||Initial Reviews Released (Research Papers Track Only)|
|July 3, 2019||Author Response Due (Research Papers Track Only)|
|July 11, 2019||Acceptance Notifications (All Tracks)|
|August 1, 2019||Camera-Ready Deadline (All Tracks)|
|August 3, 2019||Artifact Evaluation Deadline|
|August 30, 2019||Artifact Evaluation Notifications|
|October 8-9, 2019||AIIDE 2019 Workshops|
|October 10-12, 2019||AIIDE 2019 Main Conference|
The special topic of this year is “Human-Centered Evaluation.” Evaluating intelligent systems for digital entertainment can be challenging because these systems often have to account for human factors while teaching, engaging, and entertaining human players. Further, some intelligent systems for digital entertainment have primarily humanistic, artistic, and expressive purposes, for which empirical evaluation is often not well-suited. These characteristics can render traditional evaluation methodologies used in artificial intelligence unfit for digital entertainment. This year we encourage submissions introducing novel methodologies for evaluating intelligent systems for digital entertainment. We also encourage all authors to consider human-centered evaluation methodologies in their submissions.
Following is a (non-comprehensive) list of topics that fall within the scope of AIIDE:
- AI, Education, and Entertainment
- AI and Expressive Motion
- AI as Interactive Digital Entertainment
- AI in Games
- AI-Enabled Authoring Tools
- AI in Artistic Performance
- AI in Serious Games/Games for Change
- Believable Virtual Agents
- Computational Creativity
- Culturally-Situated Entertainment AI
- Critiques of Entertainment AI in the Wild
- Drama Management/Interactive Narrative
- Entertainment AI in Novel Places
- Ethical Entertainment AI
- Evaluation Methodologies and User Studies
- Heuristic search and planning
- Intelligent Cinematography
- Interactive Installations and AI
- Interpretable and Transparent AI in Entertainment
- Generative Art
- Machine learning
- Mixed-Initiative Tools in Entertainment
- Multi-agent systems
- Narrative Generation/Understanding
- Natural Language Processing in Games
- Path Planning
- Player Modeling/Analytics
- Procedural Animation
- Procedural Content Generation
- Reinforcement learning
- Robots in Entertainment
- Socially-Responsible AI in Entertainment
- Tangible and Embodied Entertainment AI
- Tools for AI in the Arts & Entertainment
- Virtual/Augmented/Mixed Reality and AI
Because work presented at AIIDE-19 crosses disciplinary boundaries, submissions will be evaluated based on their contribution type. We have two tracks for papers in the main program: Research and Practitioner.
Research track papers describe AI research results that make advances toward solving known entertainment AI problems, enable new forms of interactive digital entertainment, or use AI to improve the game design and development process. Papers presenting novel techniques should be validated in a prototype or test-bed system (e.g., game, robot, generative algorithm), but need not be tested in a commercial environment. In keeping with this year’s special topic, the research track also encourages papers that introduces and discusses novel evaluation methodologies.
Research track papers are evaluated by the highest standards of academic rigor. To guide reviewers in how to best assess papers, authors should clearly state the contribution they argue their work makes to the AIIDE research community. Additionally, authors should make clear during paper submission to what degree their work engages with the special topic. Submissions must be in PDF format and no longer than 7 pages, where page 7 must contain only references. Papers should be formatted in AAAI two-column, camera-ready style (see the AAAI Press Author Kit). All Research Track papers must be formatted for DOUBLE BLIND REVIEW with NO author or affiliation information listed. All research papers will be allocated 7 pages in the proceedings.
When formatting a paper for double blind review, authors should remove their names and affiliations from the author section on the first page. They should not remove their names from bibliography entries. When referring to citations, authors should always use third person voice, even when referring to their own work, to avoid identifying themselves as authors. For example, “Smith (2017) showed…” is correct, but “In our previous work (Smith 2017) we showed…” is incorrect. After a paper has been reviewed and accepted, authors may return to first person voice.
Authors of the Research Track will be allowed to respond to the initial set of reviews. The goal of the response is to give the authors an opportunity to briefly correct any factual mistakes in the initial set of reviews. The authors’ response will be considered in the final decisions and the reviews might be changed accordingly.
AIIDE-19 also solicits submissions from practitioners – including game developers, roboticists, and artists – on the use of artificial intelligence in games, art, and other entertainment artifacts. While these practitioners are also invited to submit to the research track, we recognize that many will have neither the time nor the inclination to prepare full-length papers for archival academic publication. These authors may instead submit a 500-word article in PDF format to the practitioner track. Practitioner track papers need not describe new technology, but they must describe relevant results to the AIIDE audience and they must be based on experience creating entertainment AI that has been publicly disseminated (including, but not limited to, AI in educational and serious games, AI-based design tools, and AI in published games). For example, we encourage submissions describing the use in real-world applications of ideas previously published in academic venues.
Authors should also include short bios describing their professional experience (not counted toward the document length). Papers should preferably be formatted in AAAI two-column, camera-ready style as above; however, Practitioner Track authors may submit their content in any reasonable format for review, and the AIIDE organizers will assign an editor to help meet publication formatting requirements for accepted work. Accepted practitioner track articles will be published as extended abstracts in the AIIDE-19 proceedings.
Policy on Prior Publication and Concurrent Review
AIIDE-19 will not consider papers that are under review for or have already been published or accepted for publication in a journal or another conference. Once submitted to AIIDE-19, authors may not submit the paper elsewhere during AIIDE’s review period. These restrictions apply only to refereed journals and conferences, not to unrefereed forums (e.g. arXiv.org) or workshops with a limited audience and without archival proceedings. Authors must confirm that their submissions conform to these requirements at the time of submission.
We invite researchers and practitioners to share demonstrations of (a) research systems in the context of existing commercial entertainment media, (b) contributions demonstrating the adoption and/or extension of AI research results in published entertainment media, (c) completely new forms of interactive digital entertainment made possible by AI research, and (d) other relevant work.
An electronic submission of a 2-page abstract (plus 1 page of references) and demonstration materials is required. Papers should be in PDF format and follow AAAI two-column, camera-ready style (see the AAAI Press Author Kit). Demo Track papers should contain author and affiliation information. Demonstration abstract review is not blind. Submissions should contain a link to the demonstration materials, which can take the form of a recorded demonstration session, an executable version of the demonstration with written instructions, or a detailed description of the demonstration heavily illustrated with screenshots. The abstract will be published in the AIIDE proceedings, but all demonstrations must be conducted live at AIIDE-19. Submissions will be judged on technical merit, accessibility to developers and researchers, originality, presentation, and significance. Complete games and playable experiences are best suited for the playable experience track.
AIIDE-19 invites proposals for half-day, one-day, and two-day workshops. Workshop participants will have the opportunity to meet and discuss issues with a selected focus, providing an informal setting for exchanging ideas. The format of workshops will be determined by their organizers. Organizers are encouraged to propose alternative formats beyond paper/poster presentations – formats such as working groups, game jams, “proposal jams,” and AI competitions are encouraged.
Workshop proposals should contain: 1) a brief description of the workshop, including the workshop’s goals and focus, 2) whether the proposed workshop is new or a continuation of a previous series of meetings, 3) a preliminary description of the workshop’s format and rough schedule, including desired length, 4) whether the workshop intends to have peer-reviewed papers published in the AIIDE-19 Workshop Proceedings, 5) the names, affiliation, and contact information of the workshop’s organizing committee, specifying the primary contact person and (optional) a preliminary program committee. Proposals for workshops should be about two (2) to three (3) pages in length in the recommended AAAI style formatting.
Please note that, as AAAI Press no longer publishes workshop proceedings as technical reports, AIIDE-19 will publish and archive its workshops proceedings as a single volume on CEUR Workshop Proceedings (CEUR-WS.org). Workshop organizers are expected to work with their authors to ensure their camera-ready versions follow the AAAI style formatting for the proceedings.
Workshop proposals should be submitted directly to the Workshops and Tutorials chair via email: Mark Nelson firstname.lastname@example.org
AIIDE-19 invites proposals for tutorials about current methods, tools, and/or technologies relevant to AI and interactive digital entertainment. A tutorial should be quarter, half, or full day in length. We strongly encourage tutorial presenters to provide opportunities for significant hands-on experience using current or emerging AI techniques. Members of all segments of the AIIDE community including industry researchers are encouraged to submit proposals. The format of tutorials will be determined by their organizers. Proposals for tutorials should be about one (1) to two (2) pages in length, describing 1) the goals of the tutorial, 2) what format the tutorial will take place, 3) who is the target audience, and 4) the anticipated outcome of the tutorial. Please also specify any technical support requirement necessary for the tutorial. AAAI two-column, camera-ready style formatting is not required, but suggested.
Tutorial proposals should be submitted directly to the Workshops and Tutorials Chair via email: Mark Nelson email@example.com
Indie developers, industry professionals, and researchers who are developing innovative games or other interactive media (“playable experiences”) with AI are invited to submit their work to the playable experiences track. We welcome playable experiences that involve some articulable innovation in the use of AI that directly affects the user’s experience. This includes novel game designs that leverage existing AI techniques, as well as innovations in the techniques themselves that lead to new kinds of playable experiences. Though submissions to the Playable Experience Track need not adhere to traditional definitions of “game,” they should be centered around human interaction and play. For example, AI-composed musical performances for audience consumption would be more at home in the demo track. Alternatively, participatory AI-facilitated musical theatre would be welcomed and encouraged as a playable experience. Playable experience submissions should be sufficiently complete and polished enough for new users to play them.
Authors should submit a 500-word artist’s statement or extended abstract describing the impetus behind the playable experience, how AI has motivated its design (or vice versa), and what they see as its primary innovation(s). Submissions should be in PDF format and preferably follow AAAI two-column, camera-ready style as above; however, Playable Experience authors may submit their content in any reasonable format for review, and AIIDE will assign an editor to help meet publication formatting requirements for accepted work. It should also include a publicly accessible link to a web-based, mobile, or downloadable player experience, as well as instructions for how to play it. This link must remain live at least through the end of the conference. If the playable experience cannot be remotely distributed (e.g., it is an installation piece situated in a physical context), then links documenting the experience with video of a complete playthrough should be provided. The peer review process for playable experiences is not blind. The abstract will be published in the conference proceedings. Authors will have the opportunity to show their playable experience during the evening reception of the AIIDE-19 conference. Playable experience authors are expected to attend the conference in-person to showcase their work. The conference organizers are currently exploring opportunities for providing travel support to facilitate participation of authors with financial need. Looking for inspiration? See examples of previously accepted playable experiences. Research prototypes, AI-based software tools, and non-interactive systems are best suited for the demo track.
AIIDE-19 invites paper submissions from early- to mid-career graduate students to the doctoral consortium. The ideal candidate has settled on a general direction for their research, but has not advanced so far that feedback from senior researchers and the community will not significantly impact their dissertation. Submissions should provide an overview of the author’s research to date, as well as outline directions for future research. Submissions will be reviewed for their relevance to AIIDE, technical quality, research promise, and prospective benefits yielded by the student’s participation in the doctoral consortium (both to the student and conference). The doctoral consortium will pair students with senior members of the AIIDE community to provide mentorship and feedback on research and related topics. In addition, participants in the doctoral consortium will have the opportunity to give oral presentations on their work to the broader AIIDE community.
Submissions to the doctoral consortium should consist of a 2-page abstract describing the student’s proposed doctoral research (plus 1 page of references) in PDF format, and they should follow AAAI two-column, camera-ready style (see the AAAI Press Author Kit). Authors should also provide a short (1 page or less) personal statement about how they hope to benefit from the DC and an academic CV. The personal statement and CV will help the program committee assess the candidate’s prior research activity and facilitate matching with a senior mentor. Accepted abstracts will be published alongside the conference proceedings, and they will be archived in the AAAI digital library. CVs and personal statements will only be used for reviewing purposes and will not be published.
This year, AIIDE will again include an Artifact Evaluation, a chance for authors of accepted papers & posters to submit a companion software artifact with their paper. Example types of artifacts include stand-alone software, web applications, datasets, plug-ins/extensions for existing tools, social media bots, and others.
The purposes of the artifact evaluation are:
- To promote reproducibility of our research results by reviewing the claims made in the paper and how well they are supported by the corresponding software;
- To promote reuse by encouraging authors to release software that is well-documented and easy to use by peers;
- To recognize software artifacts as important scholarly contributions in addition to the paper itself.
All submitted artifacts will be stringently peer reviewed through a separate review process from the main conference. Artifact evaluation is an optional round of additional reviewing available to authors of accepted papers and posters; the quality of artifacts will not affect acceptance decisions for main conference papers in any way. One companion artifact may be submitted per paper. Artifacts may only be submitted if they are associated with an accepted paper or poster in the main conference.
Starcraft AI Competition
AIIDE-19 will host the Tenth Annual Starcraft AI Competition. Participants are given the task of building the best performing AI system for the popular real-time strategy game StarCraft Brood War (Blizzard Entertainment). The goals of the competition are to provide a testbed for real-time AI systems and to promote game AI research by exhibiting AI techniques such as scripting, planning, optimization, spatial reasoning, and opponent modeling in a fast-paced popular video game. The competition will be held prior to the conference. Results will be announced at AIIDE-19. For additional information, please see: http://www.cs.mun.ca/~dchurchill/starcraftaicomp/