Dynamic Cognition Applied to Value Learning in Artificial Intelligence

Experts in Artificial Intelligence (AI) development predict that advances the of intelligent systems and agents will reshape vital areas our society. Nevertheless, if such an advance isn't done with prudence, it can result negative outcomes for humanity. For this reason, several researchers area are trying to develop a robust, beneficial, safe concept artificial intelligence. Currently, open problems field AI research arise from difficulty avoiding unwanted behaviors agents, at same time specifying what we want do. It is utmost importance have their values aligned human values, given fact cannot expect moral preferences simply because its intelligence, as discussed Orthogonality Thesis. Perhaps comes way addressing problem expressing objectives, ends, using representational cognitive methods.