Generalization in Planning

Overview

Humans are good at solving sequential decision-making problems, generalizing from a few examples, and learning skills that can be transferred to solve unseen problems. However, these problems remain long-standing open problems in AI.

This workshop will feature a synthesis of the best ideas on the topic from multiple highly active research communities. On the one hand, recent advances in deep-reinforcement learning have led to data-driven methods that provide strong short-horizon reasoning and planning, with open problems regarding sample efficiency, generalizability and transferability. On the other hand, advances and open questions in the AI planning community have been complementary, featuring robust analytical methods that provide sample-efficient generalizability and transferability for long-horizon sequential decision making, with open problems in short-horizon control and in the design and modeling of representations.

We welcome submissions addressing the problem of generalizable and transferable learning in all forms of sequential decision making. This event represents the seventh edition of the recurring GenPlan series of Workshops.

Call for Papers

The workshop will focus on research related to all aspects of learning, generalization, and transfer in sequential decision-making (SDM). This topic features technical problems that are of interest not only in multiple sub-fields of AI research (including reinforcement learning, automated planning, and learning for knowledge representation) but also in other fields of research, including formal methods and program synthesis. We will welcome submissions that address formal as well as empirical issues on topics such as:

• Formulations of generalized SDM problems.
• Representations, learning, and synthesis for generalized plans and policies.
• Learning for transfer and generalization in reinforcement learning.
• Learning and representing hierarchical policies and behaviors for SDM.
• Learning and synthesis of generalizable solutions for SDM problem classes.
• Learning paradigms, representations, and algorithms for transferring learned knowledge and solutions to new SDM problems.
• Learning and representing generalized Q/V functions and heuristics for plan and policy generalization.
• Learning high-level models and hierarchical solutions for generalizable SDM.
• Neuro-symbolic approaches for generalization and transfer in SDM.
• Few-shot learning and transfer for SDM.
• Meta-learning for generalizable policies.
• Learning for program synthesis.
• Learning domain control knowledge and partial policies.
• Generalization and transfer in robot planning problems.
• Representation of solution structures that enable generalization and transfer.

Submission Guidelines

Submissions can describe either work in progress or mature work that would be of interest to researchers working on generalization in planning. We also welcome “highlights” papers summarizing and highlighting results from multiple recent papers by the authors. Preference will be given to new work (including highlights) and work in progress rather than exact resubmissions of previously published work.

Submissions of papers being reviewed at other venues (NeurIPS, CoRL, AAAI, ICRA, ICLR, AAMAS, CVPR, etc.) are welcome since GenPlan 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.

Two types of papers can be submitted:

• full technical papers with the length of up to 9 pages + references
• short papers with the length between 3 and 5 pages + references

Submissions should use the NeurIPS paper format. The papers should adhere to the NeurIPS Code of Conduct and NeurIPS policy on using LLMs for writing in their paper. Papers can be submitted via OpenReview at https://openreview.net/group?id=NeurIPS.cc/2023/Workshop/GenPlan.

Important Dates

Invited Speakers

Feryal Behbahani

Google DeepMind

Giuseppe De Giacomo

University of Oxford

Hector Geffner

RWTH Aachen University and Linköping University

Roberta Raileanu

Meta AI

Peter Stone

The University of Texas at Austin and Sony AI

Amy Zhang

The University of Texas at Austin and Meta AI

Related Workshops

This workshop builds upon GenPlan workshop series.

• Workshop on Generalization in Planning at IJCAI-ECAI 2022
• Workshop on Generalization in Planning at IJCAI 2021
• Workshop on Generalization in Planning at AAAI 2020
• Workshop on Reasoning about Actions and Processes: Highlights of Recent Advances at ICAPS 2019
• Workshop on Reasoning about Actions and Processes: Highlights of Recent Advances at KR 2018
• Workshop on Generalized Planning at ICAPS 2017
• Workshop on Generalized Planning at AAAI 2011
• Workshop on Generalized Planning: Macros, Loops, Domain Control at ICAPS 2009

Committees

Organizing Committee

Pulkit Verma

Arizona State University, USA

Siddharth Srivastava

Arizona State University, USA

Aviv Tamar

Technion - Israel Institute for Technology, Israel

Felipe Trevizan

Australian National University, Australia

Advisory Board

• Blai Bonet, Universitat Pompeu Fabra, Spain, and Universidad Simón Bolívar, Venezuela.
• Giuseppe De Giacomo, University of Oxford, United Kingdom.
• Hector Geffner, RWTH Aachen University, Germany and Linköping University, Sweden.
• Anders Jonsson, Universitat Pompeu Fabra, Spain.
• Sheila McIlraith, The University of Toronto, Canada.
• Siddharth Srivastava, Arizona State University, USA.
• Peter Stone, The University of Texas at Austin, USA and Sony AI.
• Sylvie Thiébaux, Australian National University, Australia and Université de Toulouse, France.
• Shlomo Zilberstein, The University of Massachusetts Amherst.

Program Committee

• Blai Bonet, Universitat Pompeu Fabra, Spain, and Universidad Simón Bolívar, Venezuela.
• Rohan Chitnis, Meta Reality Labs, USA.
• Khen Elimelech, Rice University, USA.
• Raquel Fuentetaja, Universidad Carlos III de Madrid, Spain.
• Priyanka Golia, National University of Singapore, Singapore and Indian Institute of Technology Kanpur, India.
• Sergio Jiménez Celorrio, Universitat Politècnica de València, Spain.
• Anders Jonsson, Universitat Pompeu Fabra, Spain.
• Rushang Karia, Arizona State University, USA.
• Erez Karpas, Technion - Israel Institute of Technology, Israel.
• Harsha Kokel, IBM Research, USA.
• Reuth Mirsky, Bar Ilan University, Israel.
• Rashmeet Kaur Nayyar, Arizona State University, USA.
• Eva Onaindia, Universitat Politècnica de València, Spain.
• Ron Petrick, Heriot-Watt University, United Kingdom.
• Javier Segovia-Aguas, Universitat Pompeu Fabra, Spain.
• Naman Shah, Arizona State University, USA.
• Wiliam Shen, Massachusetts Institute of Technology, USA.
• Tom Silver, Massachusetts Institute of Technology, USA.
• Roni Stern, Palo Alto Research Center, USA and Ben Gurion University of the Negev, Israel.
• Matthew E. Taylor, University of Alberta, Canada.
• Sam Toyer, University of California Berkeley, USA.
• Ev Zisselman, Technion - Israel Institute of Technology, Israel.