The goal of the sequence is to motivate AIXI as an agent foundations research agenda. I will attempt to formulate and hopefully resolve some agent foundations problems rigorously within the AIXI framework and discuss alignment of AIXI-like models. This will probably include drawing on or linking the papers I write over the course of my PhD, along with more informal discussions like this one. The theory of impact for this sequence is to establish AIXI as a standard paradigm for agent foundations and hopefully elicit more academic-quality papers + find collaborators.
Could you say more about where the whole sequence is going / what motivated it? I am curious.
The goal of the sequence is to motivate AIXI as an agent foundations research agenda. I will attempt to formulate and hopefully resolve some agent foundations problems rigorously within the AIXI framework and discuss alignment of AIXI-like models. This will probably include drawing on or linking the papers I write over the course of my PhD, along with more informal discussions like this one. The theory of impact for this sequence is to establish AIXI as a standard paradigm for agent foundations and hopefully elicit more academic-quality papers + find collaborators.