Dynamic Models Applied to Value Learning in Artificial Intelligence

Abstract

Experts in Artificial Intelligence (AI) development predict that advances in intelligent systems and agents will reshape vital areas of our society. Nevertheless, if such an advance is not made prudently, it can result in adverse outcomes for humanity. For this reason, several researchers in the area are trying to develop a robust, beneficial, and safe concept of AI for the preservation of human society at large. Currently, several of the open problems in the field of AI research arise from the difficulty of avoiding unwanted behaviors of intelligent agents and systems, and at the same time specifying what we want such systems to do, especially when we look for the possibility of intelligent agents acting in several domains over the long term. It is of utmost importance that artificially intelligent agents have their values aligned with human values, given the fact that we cannot expect an AI to develop human moral values simply because of its intelligence, as discussed in the Orthogonality Thesis. This difficulty stems from the way we address the problem of expressing objectives, values, and ends using representational cognitive methods. A solution to this problem would be the dynamic approach proposed by Dreyfus, whose phenomenological philosophy shows that, in several aspects, the human experience of being-in-the-world is not well represented by symbolic or connectionist cognitive methods, especially regarding the question of learning values. A possible approach to this problem would be to use theoretical models such as SED (situated embodied dynamics) to address value learning in AI.

BibTeX

@article{DBLP:journals/corr/abs-2005-05538,
  author       = {Nicholas Kluge Corr{\^{e}}a and
                  Nythamar de Oliveira},
  title        = {Dynamic Models Applied to Value Learning in Artificial Intelligence},
  journal      = {CoRR},
  volume       = {abs/2005.05538},
  year         = {2020},
  url          = {https://arxiv.org/abs/2005.05538},
  eprinttype    = {arXiv},
  eprint       = {2005.05538},
  timestamp    = {Thu, 14 May 2020 16:56:02 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2005-05538.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}