In this fourth workshop, we continue to explore an expanding field of research that attempts to build systems that can learn without human intervention and with little or no hard-wired domain knowledge, as would a newborn child or animal. The theme for this workshop is learning groundings. We wish to explore how to ground learned objects efficiently in online self-guided exploratory learning.
As we grapple with constructing intricate A.I. systems, such as robots and other complex cyber-physical systems (CPS), and as these systems increasingly rely on machine learning for their efficacy in their intended environments, the role of human intervention is proving to be a hindrance. In this context, the necessity and potential advantages of Situated Self-guided Learning (SSL) are coming to the fore.
How do intelligent systems, such as humans and software agents, learn about the world? They should primarily learn about themselves and their environment and how the two interact effectively through exploration and self-motivated experimentation. Many learning systems being proposed continue to ignore the fundamental mechanisms underlying self-motivated learning through experience in the open world that could ultimately lead to intelligent behaviors such as (for example) how to recognize objects through visual and other senses, how to move another object to reach an object otherwise out of reach, and how to use those objects as tools, by experimenting. Higher-level learning (e.g.) the use of specialized tools, can be taught both by example and by building upon existing learned competencies. Historically, this approach has seemed difficult due to the run-time computation burden and the need for large memories. In addition, training time has been seen as limiting. Today, processors are more powerful and cheaper, and large memories are increasingly less of an obstacle.
As with prior workshops, abstracts are requested before the workshop, and final versions of papers will be due after the workshop for publication in the workshop proceedings. This is a workshop with a primary goal of discussion. The abstracts are intended to stimulate and focus discussion. Authors wishing to publish an extended version of their abstracts as a paper in our published volume are invited to submit post-workshop papers, but a paper or abstract is not a requirement for attendance. All received papers will be reviewed by the program committee, and authors can submit corrected versions after considering reviewers’ comments. We aim to discuss important issues in Situated Self-guided Learning and share our workshop results as a proceedings volume.
Abstracts and Papers will be accepted in all relevant areas, including, but not limited to, the following:
• Grounded learning, representations, and algorithms
• Online learning, representations, and algorithms
• Intrinsic motivations
• Inspirations for animal and human intelligence
• Developmental and constructivist learning; Integrated language and visual learning.
• Abstract due date August 30th, 2024
• Workshop dates September 12th and 13th, 2024
• Final paper due date October 20th, 2024
• Reviewers feedback November 3rd, 2024
• Final copy due December 20th, 2024.
Wednesday 11 September
19:00 - 21:00 Welcome Reception
Thursday 12 September
8:30 - 10:30 Introduction and Technical Sessions
10:30 - 10:50 Refreshments and Biscuits
10:50 - 13:00 Technical Sessions
13:00 - 14:00 Cooked Lunch
14:00 - 15:30 Technical Sessions
15:30 - 15:50 Refreshments and Biscuits
15:50 - 17:30 Technical Sessions
19:00 Formal Dinner
Friday 13 September
8:30 - 10:30 Introduction and Technical Sessions
10:30 - 10:50 Refreshments and Biscuits
10:50 - 13:00 Technical Sessions
13:00 - 14:00 Cooked Lunch
14:00 - 15:30 Technical Sessions
15:30 - 15:50 Refreshments and Biscuits
15:50 - 17:30 Technical Sessions
• Volume 192 Proceedings of the Third IWSSL Workshop
• Volume 159 Proceedings of the Second IWSSL Workshop
• Volume 131 Proceedings of the First IWSSL Workshop
The post-proceedings of IWSSL 2024 will be published as a Springer LNCS volume. Authors should consult Springer’s Instructions for Authors of Proceedings and use either the LaTeX or the Word templates provided on the authors’ page to prepare their papers.
• Professor Kristinn Thorisson (Reykjavik UniversiProfessor Olivier Georgeon (Catholic University of Lyon, UCLy)
• Dr. Paul Robertson (DOLL Inc.)
• Dr. Cyrus Shaoul (Leela.ai)
• Henry Minsky (Leela.ai)
• Dr. Robert Laddaga (DOLL Inc.)
