An introduction to Kolmogorov complexity and its applications (2nd ed.)
An introduction to Kolmogorov complexity and its applications (2nd ed.)
ACM SIGGRAPH Computer Graphics
Markov Decision Processes: Discrete Stochastic Dynamic Programming
Markov Decision Processes: Discrete Stochastic Dynamic Programming
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Learning Dynamic Bayesian Networks
Adaptive Processing of Sequences and Data Structures, International Summer School on Neural Networks, "E.R. Caianiello"-Tutorial Lectures
The VIS-5D system for easy interactive visualization
VIS '90 Proceedings of the 1st conference on Visualization '90
Universal Artificial Intelligence: Sequential Decisions Based On Algorithmic Probability
Universal Artificial Intelligence: Sequential Decisions Based On Algorithmic Probability
Proceedings of the 2008 conference on Artificial General Intelligence 2008: Proceedings of the First AGI Conference
Delusion, survival, and intelligent agents
AGI'11 Proceedings of the 4th international conference on Artificial general intelligence
Rational universal benevolence: simpler, safer, and Wiser than "friendly AI"
AGI'11 Proceedings of the 4th international conference on Artificial general intelligence
AGI'11 Proceedings of the 4th international conference on Artificial general intelligence
Avoiding unintended AI behaviors
AGI'12 Proceedings of the 5th international conference on Artificial General Intelligence
| Hi-index | 0.00 |
There is considerable interest in ethical designs for artificial intelligence (AI) that do not pose risks to humans. This paper proposes using elements of Hutter's agent-environment framework to define a decision support system for simulating, visualizing and analyzing AI designs to understand their consequences. The simulations do not have to be accurate predictions of the future; rather they show the futures that an agent design predicts will fulfill its motivations and that can be explored by AI designers to find risks to humans. In order to safely create a simulation model this paper shows that the most probable finite stochastic program to explain a finite history is finitely computable, and that there is an agent that makes such a computation without any unintended instrumental actions. It also discusses the risks of running an AI in a simulated environment.