Model-based Utility Functions

v1v2 (latest)

Model-based Utility Functions

16 November 2011

ArXiv (abs)PDF HTML

Papers citing "Model-based Utility Functions"

9 / 9 papers shown

Title
Reward Tampering Problems and Solutions in Reinforcement Learning: A Causal Influence Diagram Perspective Tom Everitt Marcus Hutter Ramana Kumar Victoria Krakovna 105 97 0 13 Aug 2019
Categorizing Wireheading in Partially Embedded Agents Arushi G. K. Majha Sayan Sarkar Davide Zagami 41 3 0 21 Jun 2019
Modeling AGI Safety Frameworks with Causal Influence Diagrams Tom Everitt Ramana Kumar Victoria Krakovna Shane Legg AI4CE 81 22 0 20 Jun 2019
AGI Safety Literature Review Tom Everitt G. Lea Marcus Hutter AI4CE 86 116 0 03 May 2018
AI Safety Gridworlds Jan Leike Miljan Martic Victoria Krakovna Pedro A. Ortega Tom Everitt Andrew Lefrancq Laurent Orseau Shane Legg 158 255 0 27 Nov 2017
Concrete Problems in AI Safety Dario Amodei C. Olah Jacob Steinhardt Paul Christiano John Schulman Dandelion Mané 324 2,407 0 21 Jun 2016
Avoiding Wireheading with Value Reinforcement Learning Tom Everitt Marcus Hutter AI4CE 141 44 0 10 May 2016
Self-Modification of Policy and Utility Function in Rational Agents Tom Everitt Daniel Filan Mayank Daswani Marcus Hutter 82 29 0 10 May 2016
Ethical Artificial Intelligence B. Hibbard 201 10 0 05 Nov 2014