國立虎尾科技大學 |

Policy Optimization for Long-Term Fairness in Decision Systems.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Policy Optimization for Long-Term Fairness in Decision Systems./
作者:	Yu, Eric Yang.
面頁冊數:	1 online resource (36 pages)
附註:	Source: Masters Abstracts International, Volume: 85-12.
Contained By:	Masters Abstracts International85-12.
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9798383087060

Policy Optimization for Long-Term Fairness in Decision Systems.
Yu, Eric Yang.

Policy Optimization for Long-Term Fairness in Decision Systems. - 1 online resource (36 pages)

Source: Masters Abstracts International, Volume: 85-12.

Thesis (M.S.)--University of California, San Diego, 2024.

Includes bibliographical references

Long-term fairness is an important factor of consideration in designing and deploying learning-based decision systems in high-stake decision-making contexts. Recent work has proposed the use of Markov Decision Processes (MDPs) to formulate decision-making with long-term fairness requirements in dynamically changing environments, and demonstrated major challenges in directly deploying heuristic and rule-based policies that worked well in static environments. We show that policy optimization methods from deep reinforcement learning can be used to find strictly better decision policies that can often achieve both higher overall utility and less violation of the fairness requirements, compared to previously-known strategies. In particular, we propose new methods for imposing fairness requirements in policy optimization by regularizing the advantage evaluation of different actions. Our proposed methods make it easy to impose fairness constraints without reward engineering or sacrificing training efficiency. We perform detailed analyses in three established case studies, including attention allocation in incident monitoring, bank loan approval, and vaccine distribution in population networks.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798383087060Subjects--Topical Terms:

573171
Computer science.
Subjects--Index Terms:

Markov Decision ProcessesIndex Terms--Genre/Form:

554714
Electronic books.

Policy Optimization for Long-Term Fairness in Decision Systems.
LDR:02519ntm a22003737 4500 001 1150212
005 20241022111615.5
006 m o d
007 cr bn ---uuuuu
008 250605s2024 xx obm 000 0 eng d
020 $a 9798383087060
035 $a (MiAaPQ)AAI31301839
035 $a AAI31301839
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Yu, Eric Yang. $3 1476654
245 1 0 $a Policy Optimization for Long-Term Fairness in Decision Systems.
264 0 $c 2024
300 $a 1 online resource (36 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 85-12.
500 $a Advisor: Gao, Sicun.
502 $a Thesis (M.S.)--University of California, San Diego, 2024.
504 $a Includes bibliographical references
520 $a Long-term fairness is an important factor of consideration in designing and deploying learning-based decision systems in high-stake decision-making contexts. Recent work has proposed the use of Markov Decision Processes (MDPs) to formulate decision-making with long-term fairness requirements in dynamically changing environments, and demonstrated major challenges in directly deploying heuristic and rule-based policies that worked well in static environments. We show that policy optimization methods from deep reinforcement learning can be used to find strictly better decision policies that can often achieve both higher overall utility and less violation of the fairness requirements, compared to previously-known strategies. In particular, we propose new methods for imposing fairness requirements in policy optimization by regularizing the advantage evaluation of different actions. Our proposed methods make it easy to impose fairness constraints without reward engineering or sacrificing training efficiency. We perform detailed analyses in three established case studies, including attention allocation in incident monitoring, bank loan approval, and vaccine distribution in population networks.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
653 $a Markov Decision Processes
653 $a Policy optimization
653 $a Long-term fairness
653 $a Deep reinforcement learning
655 7 $a Electronic books. $2 local $3 554714
690 $a 0800
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of California, San Diego. $b Computer Science and Engineering. $3 1189479
773 0 $t Masters Abstracts International $g 85-12.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31301839 $z click for full text (PQDT)