Research Priorities for Robust and Beneficial Artificial Intelligence

Success in the quest for artificial intelligence has the potential to bring unprecedented benefits to humanity, and it is therefore worthwhile to investigate how to maximize these benefits while avoiding potential pitfalls. This article gives numerous examples (which should by no means be construed as an exhaustive list) of such worthwhile research aimed at ensuring that AI remains robust and beneficial.

[1]  Jstor.  The American journal of international law , 1907 .

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

[3]  Nils J. Nilsson,et al.  Artificial Intelligence, Employment, and Income , 1984, AI Mag..

[4]  Eric Horvitz,et al.  Reasoning about beliefs and actions under computational resource constraints , 1987, Int. J. Approx. Reason..

[5]  Karl Johan Åström,et al.  Adaptive Control , 1989, Embedded Digital Control with Microcontrollers.

[6]  P. Parijs.  Arguing for Basic Income: Ethical Foundations for a Radical Reform , 1992 .

[7]  Devika Subramanian,et al.  Provably Bounded Optimal Agents , 1993, IJCAI.

[8]  V. Vinge.  The coming technological singularity , 1993 .

[9]  Oren Etzioni,et al.  The First Law of Robotics (A Call to Arms) , 1994, AAAI.

[10]  A. Oswald,et al.  Unhappiness and Unemployment , 1994 .

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

[12]  Kristian J. Hammond,et al.  The Stabilization of Environments , 1995, Artif. Intell..

[13]  B. Pasik-Duncan,et al.  Adaptive Control , 1996, IEEE Control Systems.

[14]  A. D'Amato.  International law studies , 1997 .

[15]  Christopher D. Wickens,et al.  A model for types and levels of human interaction with automation , 2000, IEEE Trans. Syst. Man Cybern. Part A.

[16]  Carla E. Brodley,et al.  Machine learning techniques for the computer security domain of anomaly detection , 2000 .

[17]  R. Churchill,et al.  Autonomous Institutional Arrangements in Multilateral Environmental Agreements: A Little-Noticed Phenomenon in International Law , 2000, American Journal of International Law.

[18]  Rakesh Agrawal,et al.  Privacy-preserving data mining , 2000, SIGMOD 2000.

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

[20]  Yehuda Lindell,et al.  Privacy Preserving Data Mining , 2002, Journal of Cryptology.

[21]  G. Ragsdell.  Systems , 2002, Economics of Visual Art.

[22]  David Andre,et al.  State abstraction for programmable reinforcement learning agents , 2002, AAAI/IAAI.

[23]  Jordi Sabater-Mir,et al.  Review on Computational Trust and Reputation Models , 2005, Artificial Intelligence Review.

[24]  Yuriy Brun,et al.  Finding latent code errors via machine learning over program executions , 2004, Proceedings. 26th International Conference on Software Engineering.

[25]  Moshe Tennenholtz,et al.  Program equilibrium , 2004, Games Econ. Behav..

[26]  Wei Chu,et al.  Preference learning with Gaussian processes , 2005, ICML.

[27]  Brian J. Taylor,et al.  Methods and Procedures for the Verification and Validation of Artificial Neural Networks , 2005 .

[28]  Christopher A. Rouff,et al.  Agent Technology from a Formal Perspective , 2006 .

[29]  Bruce M. McLaren,et al.  Computational Models of Ethical Reasoning: Challenges, Initial Steps, and Future Directions , 2006, IEEE Intelligent Systems.

[30]  Diana F. Spears,et al.  Assuring the Behavior of Adaptive Agents , 2006 .

[31]  Sneha Kumar Kasera,et al.  Statistical trust establishment in wireless sensor networks , 2007, 2007 International Conference on Parallel and Distributed Systems.

[32]  Luís Moniz Pereira,et al.  Modelling morality with prospective logic , 2007, Int. J. Reason. based Intell. Syst..

[33]  Peter Asaro,et al.  How Just Could a Robot War Be , 2008 .

[34]  Stephen Omohundro,et al.  The Nature of Self-Improving Artificial Intelligence , 2008 .

[35]  C. Allen,et al.  Moral Machines: Teaching Robots Right from Wrong , 2008 .

[36]  Michael Norrish,et al.  seL4: formal verification of an OS kernel , 2009, SOSP '09.

[37]  Alan K. Mackworth.  Agents, Bodies, Constraints, Dynamics, and Evolution , 2009, AI Mag..

[38]  Henry Hexmoor,et al.  Natural human role in supervising complex control systems , 2009, J. Exp. Theor. Artif. Intell..

[39]  Interim Report from the Panel Chairs , 2009 .

[40]  Wayne D. Gray,et al.  Topics in Cognitive Science , 2009 .

[41]  André Platzer,et al.  Logical Analysis of Hybrid Systems - Proving Theorems for Complex Dynamics , 2010 .

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

[43]  Yan Liu,et al.  Applications of Neural Networks in High Assurance Systems , 2010, Applications of Neural Networks in High Assurance Systems.

[44]  Luca Pulina,et al.  An Abstraction-Refinement Approach to Verification of Artificial Neural Networks , 2010, CAV.

[45]  Joseph Y. Halpern.  I Don't Want to Think About it Now: Decision Theory with Costly Computation , 2010, KR.

[46]  Jonathan M. Smith,et al.  Preliminary design of the SAFE platform , 2011, PLOS '11.

[47]  Rajeev Alur,et al.  Formal verification of hybrid systems , 2011, 2011 Proceedings of the Ninth ACM International Conference on Embedded Software (EMSOFT).

[48]  Bart Selman,et al.  S. Russell, P. Norvig, Artificial Intelligence: A Modern Approach, Third Edition , 2011, Artif. Intell..

[49]  Carsten Willems,et al.  Automatic analysis of malware behavior using machine learning , 2011, J. Comput. Secur..

[50]  Oriol Carbonell-Nicolau.  Games and Economic Behavior , 2011 .

[51]  J. Manyika.  Big data: The next frontier for innovation, competition, and productivity , 2011 .

[52]  Clemens Hetschko,et al.  Changing Identity: Retiring from Unemployment , 2011, SSRN Electronic Journal.

[53]  John P. Sullins.  Introduction: Open Questions in Roboethics , 2011 .

[54]  Laurent Orseau,et al.  Space-Time Embedded Intelligence , 2012, AGI.

[55]  Bonnie Docherty,et al.  Losing Humanity : The Case Against Killer Robots , 2012 .

[56]  Bill Hibbard,et al.  Avoiding Unintended AI Behaviors , 2012, AGI.

[57]  Nick Bostrom,et al.  The Superintelligent Will: Motivation and Instrumental Rationality in Advanced Artificial Agents , 2012, Minds and Machines.

[58]  B. Selman,et al.  Interim Report from the Panel Chairs: AAAI Presidential Panel on Long-Term AI Futures , 2012 .

[59]  Roman V. Yampolskiy,et al.  Leakproofing the Singularity Artificial Intelligence Confinement Problem , 2012 .

[60]  Martin Kiefel,et al.  Quasi-Newton Methods: A New Direction , 2012, ICML.

[61]  Kathleen Fisher.  HACMS: high assurance cyber military systems , 2012, HILT.

[62]  Joseph Y. Halpern,et al.  Game theory with translucent players , 2013, TARK.

[63]  Y. Vanderborght.  Basic income. An anthology of contemporary research. , 2013 .

[64]  N. Weaver.  Paradoxes of rational agency and formal systems that verify their own soundness , 2013, 1312.3626.

[65]  Fritz Allhoff,et al.  Routledge Handbook of Ethics and War: Just War Theory in the 21st Century , 2013 .

[66]  J. Manyika,et al.  Disruptive technologies: Advances that will transform life, business, and the global economy , 2013 .

[67]  A D Wissner-Gross,et al.  Causal entropic forces. , 2013, Physical review letters.

[68]  J. Mokyr,et al.  Secular stagnation? Not in your life , 2014 .

[69]  Matthew C. Waxman,et al.  Adapting the Law of Armed Conflict to Autonomous Weapon Systems , 2014 .

[70]  Bill Hibbard,et al.  Ethical Artificial Intelligence , 2014, Mar/Apr 2020.

[71]  Christian Blum,et al.  Towards an Ethical Robot: Internal Models, Consequences and Ethical Action Selection , 2014, TAROS.

[72]  Joseph Y. Halpern,et al.  Decision Theory with Resource-Bounded Agents , 2014, Top. Cogn. Sci..

[73]  Michael Fisher,et al.  Practical verification of decision-making in agent-based autonomous systems , 2013, Automated Software Engineering.

[74]  Ryan Calo.  Robotics and the Lessons of Cyberlaw , 2014 .

[75]  Heather Roff,et al.  The Strategic Robot Problem: Lethal Autonomous Weapons in War , 2014 .

[76]  D. Vladeck.  Machines without Principals: Liability Rules and Artificial Intelligence , 2014 .

[77]  R. Baldwin,et al.  Secular stagnation: facts, causes and cures , 2014 .

[78]  Ryan Calo.  The Case for a Federal Robotics Commission , 2014 .

[79]  Benja Fallenstein,et al.  Program Equilibrium in the Prisoner ’ s Dilemma via Löb ’ s Theorem , 2014 .

[80]  Roman Garnett,et al.  Sampling for Inference in Probabilistic Models with Fast Bayesian Quadrature , 2014, NIPS.

[81]  Michael Marien,et al.  Book Review: The Second Machine Age: Work, Progress, and Prosperity in a Time of Brilliant Technologies , 2014 .

[82]  Daniel Hintze.  Problem Class Dominance in Predictive Dilemmas , 2014 .

[83]  Max Tegmark.  Friendly Artificial Intelligence: The Physics Challenge , 2015, AAAI Workshop: AI and Ethics.

[84]  Benja Fallenstein,et al.  Questions of Reasoning Under Logical Uncertainty , 2015 .

[85]  Benja Fallenstein,et al.  Toward Idealized Decision Theory , 2015, ArXiv.

[86]  Nate Soares,et al.  Formalizing Two Problems of Realistic World-Models , 2015 .

[87]  Benja Fallenstein,et al.  Aligning Superintelligence with Human Interests: A Technical Research Agenda , 2015 .

[88]  Bill Hibbard.  Self-Modeling Agents and Reward Generator Corruption , 2015, AAAI Workshop: AI and Ethics.

[89]  Eric Horvitz.  One Hundred Year Study on Artificial Intelligence: Reflections and Framing , 2016 .

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

[91]  DautenhahnKerstin,et al.  Principles of robotics , 2017 .

[92]  Michael A. Osborne,et al.  The future of employment: How susceptible are jobs to computerisation? , 2017 .

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

[94]  October I.  Physical Review Letters , 2022 .