Presentations from SS14-03 Implementing Selves w/ Safe Motivational Systems & Self-Improvement

Monday, March 24 (Creating Self-Improving Selves)

What does it mean to create a self?
Mark Waser, Digital Wisdom Institute
Presentation Powerpoint

Lifelong Machine Learning and Reasoning
Daniel Silver, Acadia University
Presentation Powerpoint – with narration (216 MB) / no audio (8 MB)

Incorporating Elements of a Processual Self into Active Logic
Justin Brody, Goucher College
Presentation PDF * Proceedings PDF

Finding Faults in Autistic and Software Active Inductive Learning System
Boris Galitsky, Knowledge Trail Inc
Presentation Powerpoint * Proceedings PDF

Euclidean Automata
Andras Kornai, Budapest Institute of Technology
Presentation PDF * Proceedings PDF (from Author’s website)

Serving Up Minds: JCB and PAM P2
Michael S. P. Miller, Piaget Modeler

Premise: A Language for Cognitive Systems
Sheldon O. Linker, Linker Systems, Inc.
Presentation PDF

Reinforcement Learning and the Reward Engineering Principle
Daniel Dewey, Future of Humanity Institute
Presentation PDF * Proceedings PDF (from author’s website)

Implementation Workshop: Self-Improving Selves
Presentation PDF

Tuesday, March 25 (Safe Motivational Systems)

Experience of Crowds as a Guarantee for Safe Artificial Self
Rafal Rzepka, Hokkaido University
Proceedings PDF

AGI Ethics via Human Emotion: the Vital Link
Jeanne Dietsch, Mobilerobots Inc
Presentation Powerpoint

The Maverick Nanny with a Dopamine Drip
Richard Loosemore, Wells College
Proceedings PDF * Extended Version (from IEET)

Empowerment: a Universal Utility for Intrinsic Motivation or
What to do when you do not know what to do?
Daniel Polani, University of Hertfordshire

A Human-Value-Driven Motivational System
Morgan Waser, Virginia Commonwealth University
Presentation Powerpoint * Proceedings PDF

Ethics and Understanding & Managing the Unintended Consequences of Self-improvement
Steve Omohundro, Self-Aware Systems
Presentation Powerpoint (15 MB) * Presentation PDF (3.5 MB)

The Maximally Distributed Intelligence Explosion
Franco Cortese, IEET
Proceedings PDF

A Short Paper on Evaluation Schemes for Safe AGIs
Deepak Justin Nath
Presentation Powerpoint * Proceedings PDF

The Nuts & Bolts of Implementing a “Safe” Motivational System
Mark Waser, Digital Wisdom Institute
Presentation Powerpoint * Proceedings PDF

Wednesday, March 26

Computational Phronesis as a Possible Path toward Machine Emotional Integrity
Michal Ptaszynski, Kitami Institute of Technology

Developmental robotics: Lifelong learning and the morphogenesis of developmental structures
Pierre-Yves Oudeyer, Flowers Laboratory, Inria and Ensta ParisTech, France

Pros and Cons of Borrowing Morality from P2P Civilization
Rafal Rzepka, Hokkaido University

 Note:  AAAI copyright restrictions prevent us from re-posting/hosting Proceedings Papers (although authors may re-post them on their personal websites).  The proceedings are, however, available as AAAI Technical Report SS-14-03 (free online to AAAI members, $25 for print copies)

Comments are closed.