The focus of the workshop will be on learning and synthesis of behaviors that are applicable to broad classes of problems. This topic features technical problems that are of interest not only in multiple sub-fields of AI research (including automated planning, knowledge representation, and reinforcement learning) but also in other fields of research, including formal methods and program synthesis.
We welcome submissions that address formal as well as empirical issues on topics such as:
Formulation of generalized problems: propositional, first-order and other type of representations, and possible decomposition of such representations in terms of hierarchies, behaviors, multiple objectives, etc.
Representation of solution structures that enable generalization and transfer.
Learning high-level models for generalizable planning.
Learning and synthesis approaches for computing solutions.
Instantiation and execution of general solutions over new problem instances.
Heuristics for plan and policy generalization.
Generation and detection of good examples for few-shot generalizable planning and learning.
Program synthesis methods for solving classes of problems.
Driving domain control knowledge and partial policies with planning and learning.
Generalization in environments with partial observability and/or noise.
The workshop will feature multiple invited plenary and highlights talks as well as presentations of submitted technical and position papers. It will also include discussion sessions tuned to the topics presented at the workshop. It is scheduled for one-day.
We are glad to announce the following speakers for GenPlan ‘21 workshop:
Roni Khardon (invited plenary talk)
Sylvie Thiébaux (invited plenary talk)
Luc De Raedt (invited highlights talk)
Georgios Fainekos (invited highlights talk)
Armando Solar-Lezama (invited highlights talk)
Aviv Tamar (invited highlights talk)
Submissions can describe either work in progress or mature work that has already been published at other research venues and would be of interest to researchers working on generalization in planning. Previously published work in whole or in part may be in the form of a resubmission of a previous paper, or in the form of a position paper that overviews and cites a body of work. Submissions of papers being reviewed at other venues (AAAI, ECAI, ICAPS,...) are welcome since this is a non-archival venue and we will not require a transfer of copyright. If such papers are currently under blind review, please anonymize the submission. Technical papers may be up to 8 pages + 1 for references; position papers may be up to 2 pages including references. Accepted papers will be cited and referenced from this website to their original/camera-ready published versions.
All papers should follow IJCAI-21 formatting guidelines, and submitted via EasyChair at https://easychair.org/conferences/?conf=genplan21 .