Inferring human values for safe AGI design

Name: Inferring human values for safe AGI design
Author: Sezener, Can Eren

Title	Inferring human values for safe AGI design
Author	Sezener, Can Eren
Publication Date:	2015
Publication Place	- Springer International Publishing
Subject	Value learning, Inverse reinforcement learning, Friendly AI, Safe AGI
Type	Book
Language	English
Digital	Yes
Manuscript	No
Library:	Özyeğin University
Library Asset ID	978-3-319-21365-1
Record ID	02be57fa-1a43-4521-a5f5-7b14540ea9cf
Date	2015
Sample Text	Aligning goals of superintelligent machines with human values is one of the ways to pursue safety in AGI systems. To achieve this, it is first necessary to learn what human values are. However, human values are incredibly complex and cannot easily be formalized by hand. In this work, we propose a general framework to estimate the values of a human given its behavior.
DOI	10.1007/978-3-319-21365-1_16

View in source Özyeğin University Özyeğin University - Ottoman library catalog search

Özyeğin University

Inferring human values for safe AGI design

Author Sezener, Can Eren

Publication Date 2015

Publication Place - Springer International Publishing

Subject Value learning, Inverse reinforcement learning, Friendly AI, Safe AGI

Type Book

Language English

Digital Yes

Manuscript No

Library Özyeğin University

Library Asset ID 978-3-319-21365-1

Record ID 02be57fa-1a43-4521-a5f5-7b14540ea9cf

Date 2015

Sample Text Aligning goals of superintelligent machines with human values is one of the ways to pursue safety in AGI systems. To achieve this, it is first necessary to learn what human values are. However, human values are incredibly complex and cannot easily be formalized by hand. In this work, we propose a general framework to estimate the values of a human given its behavior.

DOI 10.1007/978-3-319-21365-1_16