Presenter
Roland Pihlakas
Roland Pihlakas, MSc in psychology, is an experienced AI software engineer who has been working on multi-objective value problems for almost 20 years, and has followed discussions on AI Safety since 2006. His thesis topic was about modelling of innate learning and planning mechanisms, which eventually form a foundation for culturally acquired language-based thought processes.
Abstract:
I will be talking about why we should consider fundamental principles from biology and economics when thinking about AI alignment, and how these considerations will help with AI safety as well. Next I will introduce multi-objective and multi-agent benchmark environments we have created for measuring the performance of machine learning algorithms and AI agents in relation to their capacity for biological and economical alignment. At the end I will mention some of the related themes and dilemmas not yet covered by these benchmarks, and describe new benchmark environments we have planned for future implementation.
