東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Towards Safe Artificial General Inte...

Everitt, Tom.

FindBook

Google Book

Amazon

博客來

Towards Safe Artificial General Intelligence.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Towards Safe Artificial General Intelligence./
作者:	Everitt, Tom.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2019,
面頁冊數:	254 p.
附註:	Source: Dissertations Abstracts International, Volume: 81-08, Section: B.
Contained By:	Dissertations Abstracts International81-08B.
標題:	Algorithms. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=27792134
ISBN:	9781392877418

Towards Safe Artificial General Intelligence.
Everitt, Tom.

Towards Safe Artificial General Intelligence. - Ann Arbor : ProQuest Dissertations & Theses, 2019 - 254 p.

Source: Dissertations Abstracts International, Volume: 81-08, Section: B.

Thesis (Ph.D.)--The Australian National University (Australia), 2019.

This item must not be sold to any third party vendors.

The field of artificial intelligence has recently experienced a number of breakthroughs thanks to progress in deep learning and reinforcement learning. Computer algorithms now outperform humans at Go, Jeopardy, image classification, and lip reading, and are becoming very competent at driving cars and interpreting natural language. The rapid development has led many to conjecture that artificial intelligence with greater-than-human ability on a wide range of tasks may not be far. This in turn raises concerns whether we know how to control such systems, in case we were to successfully build them. Indeed, if humanity would find itself in conflict with a system of much greater intelligence than itself, then human society would likely lose. One way to make sure we avoid such a conflict is to ensure that any future AI system with potentially greater-than-human-intelligence has goals that are aligned with the goals of the rest of humanity. For example, it should not wish to kill humans or steal their resources. The main focus of this thesis will therefore be goal alignment, i.e. how to design artificially intelligent agents with goals coinciding with the goals of their designers. Focus will mainly be directed towards variants of reinforcement learning, as reinforcement learning currently seems to be the most promising path towards powerful artificial intelligence. We identify and categorize goal misalignment problems in reinforcement learning agents as designed today, and give examples of how these agents may cause catastrophes in the future. We also suggest a number of reasonably modest modifications that can be used to avoid or mitigate each identified misalignment problem. Finally, we also study various choices of decision algorithms, and conditions for when a powerful reinforcement learning system will permit us to shut it down. The central conclusion is that while reinforcement learning systems as designed today are inherently unsafe to scale to human levels of intelligence, there are ways to potentially address many of these issues without straying too far from the currently so successful reinforcement learning paradigm. Much work remains in turning the high-level proposals suggested in this thesis into practical algorithms, however.

ISBN: 9781392877418Subjects--Topical Terms:

536374
Algorithms.

Towards Safe Artificial General Intelligence.
LDR:03285nmm a2200313 4500 001 2264438
005 20200423113053.5
008 220629s2019 ||||||||||||||||| ||eng d
020 $a 9781392877418
035 $a (MiAaPQ)AAI27792134
035 $a (MiAaPQ)AustNatlU1885164227
035 $a AAI27792134
040 $a MiAaPQ $c MiAaPQ
100 1 $a Everitt, Tom. $3 3409606
245 1 0 $a Towards Safe Artificial General Intelligence.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2019
300 $a 254 p.
500 $a Source: Dissertations Abstracts International, Volume: 81-08, Section: B.
500 $a Advisor: Hutter, Marcus.
502 $a Thesis (Ph.D.)--The Australian National University (Australia), 2019.
506 $a This item must not be sold to any third party vendors.
520 $a The field of artificial intelligence has recently experienced a number of breakthroughs thanks to progress in deep learning and reinforcement learning. Computer algorithms now outperform humans at Go, Jeopardy, image classification, and lip reading, and are becoming very competent at driving cars and interpreting natural language. The rapid development has led many to conjecture that artificial intelligence with greater-than-human ability on a wide range of tasks may not be far. This in turn raises concerns whether we know how to control such systems, in case we were to successfully build them. Indeed, if humanity would find itself in conflict with a system of much greater intelligence than itself, then human society would likely lose. One way to make sure we avoid such a conflict is to ensure that any future AI system with potentially greater-than-human-intelligence has goals that are aligned with the goals of the rest of humanity. For example, it should not wish to kill humans or steal their resources. The main focus of this thesis will therefore be goal alignment, i.e. how to design artificially intelligent agents with goals coinciding with the goals of their designers. Focus will mainly be directed towards variants of reinforcement learning, as reinforcement learning currently seems to be the most promising path towards powerful artificial intelligence. We identify and categorize goal misalignment problems in reinforcement learning agents as designed today, and give examples of how these agents may cause catastrophes in the future. We also suggest a number of reasonably modest modifications that can be used to avoid or mitigate each identified misalignment problem. Finally, we also study various choices of decision algorithms, and conditions for when a powerful reinforcement learning system will permit us to shut it down. The central conclusion is that while reinforcement learning systems as designed today are inherently unsafe to scale to human levels of intelligence, there are ways to potentially address many of these issues without straying too far from the currently so successful reinforcement learning paradigm. Much work remains in turning the high-level proposals suggested in this thesis into practical algorithms, however.
590 $a School code: 0433.
650 4 $a Algorithms. $3 536374
650 4 $a Artificial intelligence. $3 516317
650 4 $a Computer science. $3 523869
690 $a 0984
690 $a 0800
710 2 $a The Australian National University (Australia). $3 1952885
773 0 $t Dissertations Abstracts International $g 81-08B.
790 $a 0433
791 $a Ph.D.
792 $a 2019
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=27792134