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.)
- Model representation and learning domain models for planning
- Learning domain and action models for planning
- Representations for learned models in planning
- Learning effective heuristics and other forms of 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
*** Abstracts (electronic submission) due: December 11, 2020
*** Full Papers (electronic submission, PDF) due: December 18, 2020
*** Notification of acceptance: February 16, 2021
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!
Author GuidelinesAuthors 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. Both long and short papers will be reviewed against the standard criteria of relevance, originality, significance, clarity and soundness, and are expected to meet the high standards set by ICAPS. Short papers may be of narrower scope. For example, they can either address a highly specific issue, or propose/evaluate a small, yet important, extension of previous work or a new idea. Authors making multiple submissions must ensure that each submission has significant unique content. Papers submitted to ICAPS 2021 may not be submitted to other conferences or journals during the ICAPS 2021 review period, nor may be already under review or published in other conferences or journals. Over-length papers will be rejected without review.
Submission InstructionsAll submissions will be made electronically, through the EasyChair conference system:
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.
The proceedings will be published by AAAI Press. All accepted papers will be published in the main conference proceedings and will be presented orally at the conference (full papers will be allocated more time).
ICAPS 2021 Planning and Learning Track Chairs
Sinno Jialin Pan, Nanyang Technological University
Scott Sanner, University of Toronto