Mammalian Value Systems

Characterizing human values is a topic deeply interwoven with the sciences, humanities, art, and many other human endeavors. In recent years, a number of thinkers have argued that accelerating trends in computer science, cognitive science, and related disciplines foreshadow the creation of intelligent machines which meet and ultimately surpass the cognitive abilities of human beings, thereby entangling an understanding of human values with future technological development. Contemporary research accomplishments suggest sophisticated AI systems becoming widespread and responsible for managing many aspects of the modern world, from preemptively planning users' travel schedules and logistics, to fully autonomous vehicles, to domestic robots assisting in daily living. The extrapolation of these trends has been most forcefully described in the context of a hypothetical "intelligence explosion," in which the capabilities of an intelligent software agent would rapidly increase due to the presence of feedback loops unavailable to biological organisms. The possibility of superintelligent agents, or simply the widespread deployment of sophisticated, autonomous AI systems, highlights an important theoretical problem: the need to separate the cognitive and rational capacities of an agent from the fundamental goal structure, or value system, which constrains and guides the agent's actions. The "value alignment problem" is to specify a goal structure for autonomous agents compatible with human values. In this brief article, we suggest that recent ideas from affective neuroscience and related disciplines aimed at characterizing neurological and behavioral universals in the mammalian class provide important conceptual foundations relevant to describing human values. We argue that the notion of "mammalian value systems" points to a potential avenue for fundamental research in AI safety and AI ethics.

[1]  Noah D. Goodman,et al.  Learning the Preferences of Ignorant, Inconsistent Agents , 2015, AAAI.

[2]  Phillip R. Shaver,et al.  Handbook of attachment : theory, research, and clinical applications , 1999 .

[3]  Steve Omohundro,et al.  Autonomous technology and the greater human good , 2014, J. Exp. Theor. Artif. Intell..

[4]  I. J. Good,et al.  Speculations Concerning the First Ultraintelligent Machine , 1965, Adv. Comput..

[5]  L. Swanson.  Brain Architecture: Understanding the Basic Plan , 2002 .

[6]  L. Swanson.  Cerebral hemisphere regulation of motivated behavior 1 1 Published on the World Wide Web on 2 November 2000. , 2000, Brain Research.

[7]  Anca D. Dragan,et al.  Cooperative Inverse Reinforcement Learning , 2016, NIPS.

[8]  K. Bell,et al.  Handbook of Attachment: Theory, Research, and Clinical Applications , 2001 .

[9]  S. Porges.  Orienting in a defensive world: mammalian modifications of our evolutionary heritage. A Polyvagal Theory. , 1995, Psychophysiology.

[10]  Nick Bostrom,et al.  Future Progress in Artificial Intelligence: A Survey of Expert Opinion , 2013, PT-AI.

[11]  Ian Horswill.  Men Are Dogs (and Women Too) , 2008, AAAI Fall Symposium: Naturally-Inspired Artificial Intelligence.

[12]  J. Panksepp,et al.  The Archaeology of Mind: Neuroevolutionary Origins of Human Emotions , 2012 .

[13]  D. Chalmers.  The Singularity: a Philosophical Analysis , 2010 .

[14]  Eliezer Yudkowsky.  Artificial Intelligence as a Positive and Negative Factor in Global Risk , 2006 .

[15]  Joshua B. Tenenbaum,et al.  Bayesian Theory of Mind: Modeling Joint Belief-Desire Attribution , 2011, CogSci.

[16]  Roman V. Yampolskiy,et al.  The technological singularity , 2017 .

[17]  Nils J. Nilsson,et al.  The Quest for Artificial Intelligence , 2009 .

[18]  Owain Evans.  Learning the Preferences of Bounded Agents , 2015 .

[19]  Joshua D. Greene.  The Cognitive Neuroscience of Moral Judgment , 2010 .

[20]  William L. Ury,et al.  Getting to Yes , 2019, Boy on the Bridge.

[21]  John Salvatier,et al.  When Will AI Exceed Human Performance? Evidence from AI Experts , 2017, ArXiv.

[22]  S. Armstrong.  Towards Interactive Inverse Reinforcement Learning , 2016 .

[23]  Stephen M. Omohundro,et al.  The Basic AI Drives , 2008, AGI.

[24]  L. Cosmides,et al.  The Adapted mind : evolutionary psychology and the generation of culture , 1992 .

[25]  M. Seligman,et al.  Character Strengths and Virtues: A Handbook and Classification , 2004 .

[26]  Joshua D. Greene,et al.  How (and where) does moral judgment work? , 2002, Trends in Cognitive Sciences.

[27]  J. Stevenson.  The cultural origins of human cognition , 2001 .

[28]  Mark Zuckerberg,et al.  Why Software Is Eating the World , 2011 .

[29]  G. Clore,et al.  Disgust as Embodied Moral Judgment , 2008, Personality and Social Psychology Bulletin.

[30]  Mark O. Riedl.  Computational Narrative Intelligence: A Human-Centered Goal for Artificial Intelligence , 2016, ArXiv.

[31]  Seth D. Baum,et al.  Social choice ethics in artificial intelligence , 2017, AI & SOCIETY.

[32]  S. Dehaene,et al.  Cultural Recycling of Cortical Maps , 2007, Neuron.

[33]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[34]  Charles Kemp,et al.  How to Grow a Mind: Statistics, Structure, and Abstraction , 2011, Science.

[35]  C. Robert.  Superintelligence: Paths, Dangers, Strategies , 2017 .

[36]  J. Panksepp.  Affective Neuroscience: The Foundations of Human and Animal Emotions , 1998 .

[37]  Stuart Russell.  Should We Fear Supersmart Robots? , 2016, Scientific American.

[38]  J. Bowlby.  Attachment and loss: retrospect and prospect. , 1969, The American journal of orthopsychiatry.

[39]  Mark O. Riedl,et al.  Using Stories to Teach Human Values to Artificial Agents , 2016, AAAI Workshop: AI, Ethics, and Society.

[40]  Andrew Y. Ng,et al.  Pharmacokinetics of a novel formulation of ivermectin after administration to goats , 2000, ICML.