CFP: Intrinsically Motivated Open-Ended Learning Workshop at NeurIPS 2023

Workshop Website: https://imol-workshop.github.io

Important dates:

• Submission deadline: 25 September, 2023
• Acceptance notification: 27 October, 2023
• Workshop date: 15 or 16 December, 2023

Workshop Description (see website for more details):

How do humans develop broad and flexible repertoires of knowledge and skills? How can we design autonomous lifelong learning machines with the same abilities? The field of IMOL explores these questions through integrating research on the motivational forces, learning architectures, and developmental and environmental constraints supporting the acquisition of open-ended repertoires of skill and knowledge. 

At this full-day in-person NeurIPS workshop, we will gather speakers from a wide diversity of scientific traditions, showcase on-going research via contributed talks and poster sessions, and provide networking opportunities for research and mentorship discussions. Invited speakers include Michael Tomasello, Georg Martius, Natalia Velez, and Feryal Behbani. 

Submission Formats

We welcome 4-page submissions of empirical, technical, benchmark and opinion papers on any topics relevant to Intrinsically Motivated Open-ended Learning themes across disciplines (machine learning, cognitive sciences, philosophy, psychology, and more). Examples include, but are not limited to:

• Intrinsic motivation in machines and animals,
• Autonomous open-ended learning,
• Autonomous goal generation,
• Self-supervised representation learning,
• Hierarchical and goal-directed RL,
• Curriculum learning,
• Interplay between intrinsic and extrinsic motivations,
• Skill compositionality and chunking,
• Knowledge transfer,
• Avoiding catastrophic forgetting,
• Learning neural/probabilistic abstract representations of state, actions and skills,
• Open-ended development in children,
• Role of metacognitive representations and processes in open-ended learning,
• Playful exploration,
• Language and sociality in open-ended learning,
• Mitigation of risks of open-ended learning,
• Philosophical and ethical implications of IMOL.

Submission instructions:

Submissions must be made via OpenReview. They must be anonymized, up to 4 pages long (excluding references and appendices) and use the NeurIPS 2023 LaTeX template. Appendices can be added to the main PDF. Each paper will receive two reviews; both authors and reviewers will be anonymous throughout the process. 

The papers should report original research, provide synthesis of previous works or develop novel environments. Short opinion and review papers are welcomed. Authors can upload concise versions of parallel submissions to other conferences including the NeurIPS main conference. We accept dual submission but discourage submitting to multiple NeurIPS workshops.

All accepted papers will be available on the workshop website, but no formal workshop proceedings will be published.

For any questions, email us at [email protected] or reach us on Twitter at https://twitter.com/IMOLNeurIPS2023

all best,
The IMOL@NeurIPS 2023 Organizing Committee

https://imol-workshop.github.io/