- 10 Dec, 2021 - Abstracts Due
- 15 Dec, 2021 - Submissions Due
- 25-28 Jan, 2022 - Author Feedback
- 18 Feb, 2022 - Notification
|Submissions due||December 10, 2021 (abstracts)|
|December 15, 2021 (papers)|
|Discussion||January 25-28, 2022|
|Notification||February 18, 2022|
The Planning and Learning track aims to present research at the intersection of the fields of machine and reinforcement learning with planning and scheduling. In particular, we are interested in work that draws substantially from the objectives, techniques, or methodologies of both fields.
Topics include, but are not limited to the following:
- Reinforcement learning using planning (model-based, Bayesian, deep, etc.)
- Learning domain and action models for planning
- Representations for learned models in planning
- Learning effective heuristics and other forms of planning control knowledge
- Theoretical aspects of planning and learning
- Multi-agent planning and learning
- Planning applied to automating machine learning systems
- Learning to improve the effectiveness of planning & scheduling systems
- Applications that involve a combination of learning with planning or scheduling
Please note: papers that do not clearly make a case for their relevance to model-based planning techniques or that do not compare to model-based planning techniques may be rejected without review.
We have arranged our schedule to permit revision and resubmission of papers rejected from AAAI 2022.
- December 10, 2021 - Abstracts due (electronic submission)
- December 15, 2021 - Full Papers due (electronic submission, PDF)
- January 25-28, 2022 - Author feedback period
- February 18, 2022 - Notification of acceptance or rejection
The reference timezone for all deadlines is UTC-12. That is, as long as there is still some place anywhere in the world where the deadline has not yet passed, you are on time!
Authors may submit long papers (8 pages AAAI style plus up to one page of references) or short papers (4 pages plus up to one page of references). The type of paper must be indicated at submission time. All papers, regardless of length, will be reviewed against the standard criteria of relevance, originality, significance, clarity, soundness, and are expected to meet the same high standards set by ICAPS. Short papers may be of narrower scope, for example by addressing a highly specific issue, or proposing or evaluating a small, yet important, extension of previous work or new idea. Overlength papers will be rejected without review.
Authors making multiple submissions must ensure that each submission has significant unique content. Papers submitted to ICAPS 2022 may not be submitted to other conferences or journals during the ICAPS 2022 review period nor may they be already under review, accepted, or published in other conferences or journals. AAAI decisions will be available two weeks before the ICAPS paper submission deadline. This year, the time gap between submissions to major AI conferences is tighter than usual. We had hoped to be able to both accept submissions of papers rejected from AAAI and enable authors to submit papers rejected from ICAPS to IJCAI 2022. However, the timeline is simply too tight for us to do this and maintain the quality of the ICAPS reviewing process. So while rejected papers from AAAI will have decisions early enough to permit revision and resubmission to ICAPS, we are unable to complete our reviews in time for papers to be resubmitted to IJCAI. Specifically, as the ICAPS 2022 notification date is after IJCAI 2022 full paper submission dates, ICAPS authors will not be allowed to resubmit their papers to IJCAI while they are under review at ICAPS, because of single submission requirements of both conferences.
It is optional for authors to include a statement of the potential broader impact of their work, including its ethical aspects and future societal consequences. This statement can be included in either the main body pages or the reference page. If such a statement is not included in the paper but the reviewers deem that such a statement is necessary, then the authors will be asked to provide one during the author response period for review. If the paper is accepted, the statement provided will need to be incorporated in the camera-ready version.
All submissions will be made electronically, through the EasyChair conference system: https://www.easychair.org/conferences/?conf=icaps2022
Submitted PDF papers should be anonymous for double-blind reviewing, adhere to the page limits of the relevant track CFP/submission type (long or short), and follow the AAAI author kit instructions for formatting:
In addition to the submitted PDF paper, authors can submit supplementary material (videos, technical proofs, additional experimental results) for their paper. Please make sure that the supporting material is also anonymized. Papers should be self-contained; reviewers are encouraged, but not obligated, to consider supporting material in their decisions.
Please direct all questions to ICAPS2022@easychair.org.
ICAPS 2022 Planning and Learning Track Chairs
Anders Jonsson, Pompeu Fabra University
Scott Sanner, University of Toronto