Towards Safe Artificial General Intelligence
暂无分享,去创建一个
[1] Javier García,et al. A comprehensive survey on safe reinforcement learning , 2015, J. Mach. Learn. Res..
[2] Nick Bostrom,et al. Future Progress in Artificial Intelligence: A Survey of Expert Opinion , 2013, PT-AI.
[3] Toby Walsh. The Singularity May Never Be Near , 2017, AI Mag..
[4] James L Olds,et al. Positive reinforcement produced by electrical stimulation of septal area and other regions of rat brain. , 1954, Journal of comparative and physiological psychology.
[5] Laurent Orseau,et al. Thompson Sampling is Asymptotically Optimal in General Environments , 2016, UAI.
[6] Benja Fallenstein,et al. Problems of Self-reference in Self-improving Space-Time Embedded Intelligence , 2014, AGI.
[7] Alex Altair,et al. A Comparison of Decision Algorithms on Newcomblike Problems , 2023, ArXiv.
[8] Jan Leike,et al. Nonparametric General Reinforcement Learning , 2016, ArXiv.
[9] Marcus Hutter,et al. Bad Universal Priors and Notions of Optimality , 2015, COLT.
[10] Arif Ahmed,et al. Evidence, Decision and Causality , 2014 .
[11] Jon Bird,et al. The evolved radio and its implications for modelling the evolution of novel sensors , 2002, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600).
[12] John Schulman,et al. Concrete Problems in AI Safety , 2016, ArXiv.
[13] Christos H. Papadimitriou,et al. Elements of the Theory of Computation , 1997, SIGA.
[14] M. Schervish,et al. State-Dependent Utilities , 1990 .
[15] Kaj Sotala. How feasible is the rapid development of artificial superintelligence? , 2017 .
[16] T. Modis,et al. Forecasting the Growth of Complexity and Change , 2002 .
[17] William G. Faris. Shadows of the Mind: A Search for the Missing Science of Consciousness , 1997 .
[18] Marcus Hutter,et al. Death and Suicide in Universal Artificial Intelligence , 2016, AGI.
[19] Pieter Abbeel,et al. An Application of Reinforcement Learning to Aerobatic Helicopter Flight , 2006, NIPS.
[20] K. Eric Drexler,et al. MDL Intelligence Distillation : Exploring Strategies for Safe Access to Superintelligent Problem-Solving Capabilities , 2018 .
[21] Peter Auer,et al. Near-optimal Regret Bounds for Reinforcement Learning , 2008, J. Mach. Learn. Res..
[22] E. Rasmussen. Games and Information , 1989 .
[23] Jürgen Schmidhuber,et al. Algorithmic Theories of Everything , 2000, ArXiv.
[24] N. Goodman. Fact, Fiction, and Forecast , 1955 .
[25] James M. Joyce. The Foundations of Causal Decision Theory , 1999 .
[26] Tor Lattimore,et al. Asymptotically Optimal Agents , 2011, ALT.
[27] Guigang Zhang,et al. Deep Learning , 2016, Int. J. Semantic Comput..
[28] Stuart Armstrong,et al. Motivated Value Selection for Artificial Agents , 2015, AAAI Workshop: AI and Ethics.
[29] Jianfeng Gao,et al. Combating Reinforcement Learning's Sisyphean Curse with Intrinsic Fear , 2016, ArXiv.
[30] Scott Garrabrant,et al. Categorizing Variants of Goodhart's Law , 2018, ArXiv.
[31] Logan Engstrom,et al. Synthesizing Robust Adversarial Examples , 2017, ICML.
[32] Demis Hassabis,et al. Mastering the game of Go without human knowledge , 2017, Nature.
[33] D. Chalmers. The Singularity: a Philosophical Analysis , 2010 .
[34] Stefan Schaal,et al. Is imitation learning the route to humanoid robots? , 1999, Trends in Cognitive Sciences.
[35] David J. Jilk,et al. Anthropomorphic reasoning about neuromorphic AGI safety , 2017, J. Exp. Theor. Artif. Intell..
[36] Marcus Hutter,et al. A Philosophical Treatise of Universal Induction , 2011, Entropy.
[37] Benja Fallenstein,et al. Aligning Superintelligence with Human Interests: A Technical Research Agenda , 2015 .
[38] Ernest Davis,et al. Ethical guidelines for a superintelligence , 2015, Artif. Intell..
[39] Matthias Scheutz,et al. The “big red button” is too late: an alternative model for the ethical evaluation of AI systems , 2018, Ethics and Information Technology.
[40] Jürgen Schmidhuber,et al. World Models , 2018, ArXiv.
[41] Clara Neppel. AI: Intelligent machines, smart policies , 2018, OECD Digital Economy Papers.
[42] Marcus Hutter,et al. Count-Based Exploration in Feature Space for Reinforcement Learning , 2017, IJCAI.
[43] Nate Soares,et al. Logical Induction , 2016, Electron. Colloquium Comput. Complex..
[44] Markus Müller,et al. Stationary algorithmic probability , 2006, Theor. Comput. Sci..
[45] Anind K. Dey,et al. Maximum Entropy Inverse Reinforcement Learning , 2008, AAAI.
[46] Roman V. Yampolskiy,et al. Artificial Superintelligence: A Futuristic Approach , 2015 .
[47] Nick Bostrom,et al. Racing to the precipice: a model of artificial intelligence development , 2016, AI & SOCIETY.
[48] Roman V Yampolskiy,et al. Responses to catastrophic AGI risk: a survey , 2014 .
[49] Tor Lattimore,et al. Universal Prediction of Selected Bits , 2011, ALT.
[50] Laurent Orseau,et al. Self-Modification and Mortality in Artificial Agents , 2011, AGI.
[51] Peter Norvig,et al. Artificial Intelligence: A Modern Approach , 1995 .
[52] C. Aitken,et al. The logic of decision , 2014 .
[53] John R. Searle,et al. Minds, brains, and programs , 1980, Behavioral and Brain Sciences.
[54] Anca D. Dragan,et al. Should Robots be Obedient? , 2017, IJCAI.
[55] Shane Legg,et al. Human-level control through deep reinforcement learning , 2015, Nature.
[56] Demis Hassabis,et al. Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm , 2017, ArXiv.
[57] Wendy Hall,et al. Growing the artificial intelligence industry in the UK , 2017 .
[58] Michael I. Jordan,et al. MASSACHUSETTS INSTITUTE OF TECHNOLOGY ARTIFICIAL INTELLIGENCE LABORATORY and CENTER FOR BIOLOGICAL AND COMPUTATIONAL LEARNING DEPARTMENT OF BRAIN AND COGNITIVE SCIENCES , 1996 .
[59] Jessica Taylor,et al. A Formal Solution to the Grain of Truth Problem , 2016, UAI.
[60] Yi-Ling Teo. Regulating Artificial Intelligence : An Ethical Approach , 2018 .
[61] Ming Li,et al. Average Case Complexity Under the Universal Distribution Equals Worst-Case Complexity , 1992, Inf. Process. Lett..
[62] William Harper,et al. Counterfactuals and Two Kinds of Expected Utility , 1978 .
[63] Laurent Orseau,et al. Safely Interruptible Agents , 2016, UAI.
[64] Shane Legg,et al. Psychlab: A Psychology Laboratory for Deep Reinforcement Learning Agents , 2018, ArXiv.
[65] Marcus Hutter,et al. Sequential Extensions of Causal and Evidential Decision Theory , 2015, ADT.
[66] Nick Bostrom,et al. Thinking Inside the Box: Controlling and Using an Oracle AI , 2012, Minds and Machines.
[67] Tommi S. Jaakkola,et al. A causal framework for explaining the predictions of black-box sequence-to-sequence models , 2017, EMNLP.
[68] Eliezer Yudkowsky,et al. Program Equilibrium in the Prisoner ’ s Dilemma via Löb ’ s Theorem , 2014 .
[69] J. Tenenbaum,et al. Learning a commonsense moral theory , 2017, Cognition.
[70] Joan Bruna,et al. Intriguing properties of neural networks , 2013, ICLR.
[71] Laurent Orseau,et al. Optimality Issues of Universal Greedy Agents with Static Priors , 2010, ALT.
[72] Iyad Rahwan,et al. Superintelligence cannot be contained: Lessons from Computability Theory , 2016, J. Artif. Intell. Res..
[73] Shane Legg,et al. A Collection of Definitions of Intelligence , 2007, AGI.
[74] Marcus Hutter,et al. AGI Safety Literature Review , 2018, IJCAI.
[75] Dr. Marcus Hutter,et al. Universal artificial intelligence , 2004 .
[76] Dawn Song,et al. Robust Physical-World Attacks on Deep Learning Models , 2017, 1707.08945.
[77] Marcus Hutter,et al. Analytical Results on the BFS vs. DFS Algorithm Selection Problem. Part I: Tree Search , 2015, Australasian Conference on Artificial Intelligence.
[78] Stuart Armstrong,et al. Impossibility of deducing preferences and rationality from human policy , 2017, NIPS 2018.
[79] S. Baum. A Survey of Artificial General Intelligence Projects for Ethics, Risk, and Policy , 2017 .
[80] Laurent Orseau,et al. AI Safety Gridworlds , 2017, ArXiv.
[81] Ray J. Solomonoff,et al. A Formal Theory of Inductive Inference. Part I , 1964, Inf. Control..
[82] Vincent Conitzer,et al. An "Ethical" Game-Theoretic Solution Concept for Two-Player Perfect-Information Games , 2008, WINE.
[83] Mark O. Riedl,et al. Using Stories to Teach Human Values to Artificial Agents , 2016, AAAI Workshop: AI, Ethics, and Society.
[84] Andrew Y. Ng,et al. Pharmacokinetics of a novel formulation of ivermectin after administration to goats , 2000, ICML.
[85] David A. Rottenberg,et al. Compulsive thalamic self-stimulation: A case with metabolic, electrophysiologic and behavioral correlates , 1986, Pain.
[86] James Babcock,et al. Guidelines for Artificial Intelligence Containment , 2017, Next-Generation Ethics.
[87] Leslie Pack Kaelbling,et al. Planning and Acting in Partially Observable Stochastic Domains , 1998, Artif. Intell..
[88] Stuart Armstrong,et al. Low Impact Artificial Intelligences , 2017, ArXiv.
[89] Robin Cohen,et al. Towards Provably Moral AI Agents in Bottom-up Learning Frameworks , 2018, AAAI Spring Symposia.
[90] Demis Hassabis,et al. Mastering the game of Go with deep neural networks and tree search , 2016, Nature.
[91] Ramana Kumar,et al. Proof-Producing Reflection for HOL - With an Application to Model Polymorphism , 2015, ITP.
[92] Jonathon Shlens,et al. Explaining and Harnessing Adversarial Examples , 2014, ICLR.
[93] Raymond C. Kurzweil,et al. The Singularity Is Near , 2018, The Infinite Desire for Growth.
[94] Kaj Sotala,et al. Superintelligence As a Cause or Cure For Risks of Astronomical Suffering , 2017, Informatica.
[95] Stephen Omohundro,et al. The Nature of Self-Improving Artificial Intelligence , 2008 .
[96] Marcus Hutter,et al. Universal Reinforcement Learning Algorithms: Survey and Experiments , 2017, IJCAI.
[97] Seán S. ÓhÉigeartaigh,et al. An AI Race for Strategic Advantage: Rhetoric and Risks , 2017, AIES.
[98] Jeffrey D. Ullman,et al. Introduction to Automata Theory, Languages and Computation , 1979 .
[99] John Salvatier,et al. When Will AI Exceed Human Performance? Evidence from AI Experts , 2017, ArXiv.
[100] Randy H. Katz,et al. A Berkeley View of Systems Challenges for AI , 2017, ArXiv.
[101] Vincent Conitzer,et al. Moral Decision Making Frameworks for Artificial Intelligence , 2017, ISAIM.
[102] I. J. Good,et al. Speculations Concerning the First Ultraintelligent Machine , 1965, Adv. Comput..
[103] Mykel J. Kochenderfer,et al. Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks , 2017, CAV.
[104] David H. Wolpert,et al. No free lunch theorems for optimization , 1997, IEEE Trans. Evol. Comput..
[105] J. Lucas. Minds, Machines and Gödel , 1961, Philosophy.
[106] Regina Barzilay,et al. Rationalizing Neural Predictions , 2016, EMNLP.
[107] Jessica Taylor,et al. Quantilizers: A Safer Alternative to Maximizers for Limited Optimization , 2016, AAAI Workshop: AI, Ethics, and Society.
[108] Brian Skyrms,et al. Causal Decision Theory , 1982 .
[109] Jessica Taylor,et al. Alignment for Advanced Machine Learning Systems , 2020, Ethics of Artificial Intelligence.
[110] Alex Graves,et al. Asynchronous Methods for Deep Reinforcement Learning , 2016, ICML.
[111] Shie Mannor,et al. Graying the black box: Understanding DQNs , 2016, ICML.
[112] D. Kahneman. Thinking, Fast and Slow , 2011 .
[113] Robert Nozick,et al. Newcomb’s Problem and Two Principles of Choice , 1969 .
[114] Nate Soares,et al. Functional Decision Theory: A New Theory of Instrumental Rationality , 2017, ArXiv.
[115] Shane Legg,et al. Deep Reinforcement Learning from Human Preferences , 2017, NIPS.
[116] Ming Li,et al. Kolmogorov Complexity and its Applications , 1991, Handbook of Theoretical Computer Science, Volume A: Algorithms and Complexity.
[117] Richard S. Sutton,et al. Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.
[118] J. Pearl. Causality: Models, Reasoning and Inference , 2000 .
[119] Risto Miikkulainen,et al. The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities , 2018, Artificial Life.
[120] M. Strathern. ‘Improving ratings’: audit in the British University system , 1997, European Review.
[121] David J. Jilk. Conceptual-Linguistic Superintelligence , 2017, Informatica.
[122] Gabriel Murray. Stoic Ethics for Artificial Agents , 2017, Canadian Conference on AI.
[123] Stephen Wolfram,et al. A New Kind of Science , 2003, Artificial Life.
[124] Kee-Eung Kim,et al. Inverse Reinforcement Learning in Partially Observable Environments , 2009, IJCAI.
[125] Haim Gaifman,et al. Reasoning with Limited Resources and Assigning Probabilities to Arithmetical Statements , 2004, Synthese.
[126] Ryan Carey,et al. Incorrigibility in the CIRL Framework , 2017, AIES.