Models of bounded or imperfect rationality. Multi-agent perspectives and applications, and Value alignment and inverse reinforcement learning, The foundations of rational agency and causality, Our areas of greatest focus so far have been However, our interests extend to a variety of other problems in the development of provably beneficial AI systems. Therefore, much of CHAI's research efforts to date have focussed on developing and communicating a new model of AI development, in which AI systems should be uncertain of their objectives, and should be deferent to humans in light of that uncertainty. This way of formulating objectives stands in contrast to the standard model for AI, in which the AI system's objective is assumed to be known completely and correctly. This means we need to somehow represent uncertainty in the objectives of AI systems. In short, any initial formal specification of human values is bound to be wrong in important ways. Currently, it is not possible to specify a formula for human values in any form that we know would provably benefit humanity, if that formula were instated as the objective of a powerful AI system. CHAI aims to reorient the foundations of AI research toward the development of provably beneficial systems.
0 Comments
Leave a Reply. |