Approving this grant; apologies for the delay! (I was waiting for Joar to create an account and then missed when he actually did.)
Travel funding for International Conference on Learning Representations
Joar Skalse
Project summary
Provide travel fundingfor a 1-week machine learning conference. Attendee will be presenting a paper on reward learning, STARC: A General Framework For Quantifying Differences Between Reward Functions, that is relevant to AI safety.
What are this project's goals and how they be achieved?
Improve the safety of AI systems by disseminating core research on this topic.
How will this funding be used?
Pay for conference ticket, round-trip flight, accommodation for a week, and food/sundries.
Who is on the team and what's their track record on similar projects?
Joar Skalse is a PhD student at Oxford, with a track record publishing strong papers like "Defining and characterizing reward gaming" and "Risks from learned optimization in advanced machine learning systems"
What are the most likely causes and outcomes if this project fails? (premortem)
People may not be interested in the paper, or they may be interested in but not build on the work.
What other funding is this person or project getting?
Funding not available from their lab at Oxford for travel funding.
Adam Gleave
7 months ago
Main points in favor of this grant
Good paper that would be exciting to disseminate. This is a very cheap way of supporting that.
Donor's main reservations
The paper is very theoretical in nature and may not end up improving AI safety in practice.
Process for deciding amount
I asked Joar for an estimate of the travel costs, checked they were reasonable, and then added my own estimate for costs for food/sundries in Vienna.
Conflicts of interest
Please disclose e.g. any romantic, professional, financial, housemate, or familial relationships you have with the grant recipient(s).
I previously supervised Joar Skalse on a related project. Joar is currently a contractor working on a separate project for my organization, FAR AI.