國立虎尾科技大學 |

What Do You Want Me to Do? Addressing Model Differences for Human-Aware Decision-Making from a Learning Perspective.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	What Do You Want Me to Do? Addressing Model Differences for Human-Aware Decision-Making from a Learning Perspective./
作者:	Gong, Ze.
面頁冊數:	1 online resource (120 pages)
附註:	Source: Dissertations Abstracts International, Volume: 84-02, Section: B.
Contained By:	Dissertations Abstracts International84-02B.
標題:	Computer engineering. -
電子資源:	click for full text (PQDT)
ISBN:	9798841776529

What Do You Want Me to Do? Addressing Model Differences for Human-Aware Decision-Making from a Learning Perspective.
Gong, Ze.

What Do You Want Me to Do? Addressing Model Differences for Human-Aware Decision-Making from a Learning Perspective. - 1 online resource (120 pages)

Source: Dissertations Abstracts International, Volume: 84-02, Section: B.

Thesis (Ph.D.)--Arizona State University, 2022.

Includes bibliographical references

As intelligent agents become pervasive in our lives, they are expected to not only achieve tasks alone but also engage in tasks with humans in the loop. In such cases, the human naturally forms an understanding of the agent, which affects his perception of the agent's behavior. However, such an understanding inevitably deviates from the ground truth due to reasons such as the human's lack of understanding of the domain or misunderstanding of the agent's capabilities. Such differences would result in an unmatched expectation of the agent's behavior with the agent's optimal behavior, thereby biasing the human's assessment of the agent's performance. In this dissertation, I focus on when these differences are due to a biased belief about domain dynamics. I especially investigate the impact of such a biased belief on the agent's decision-making process in two different problem settings from a learning perspective. In the first setting, the agent is tasked to accomplish a task alone but must infer the human's objectives from the human's feedback on the agent's behavior in the environment. In such a case, the human biased feedback could mislead the agent to learn a reward function that results in a sub-optimal and, potentially, undesired policy. In the second setting, the agent must accomplish a task with a human observer. Given that the agent's optimal behavior may not match the human's expectation due to the biased belief, the agent's optimal behavior may be viewed as inexplicable, leading to degraded performance and loss of trust. Consequently, this dissertation proposes approaches that (1) endow the agent with the ability to be aware of the human's biased belief while inferring the human's objectives, thereby (2) neutralize the impact of the model differences in a reinforcement learning framework, and (3) behave explicably by reconciling the human's expectation and optimality during decision-making.

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

Mode of access: World Wide Web

ISBN: 9798841776529Subjects--Topical Terms:

569006
Computer engineering.
Subjects--Index Terms:

Human awareIndex Terms--Genre/Form:

554714
Electronic books.

What Do You Want Me to Do? Addressing Model Differences for Human-Aware Decision-Making from a Learning Perspective.
LDR:03315ntm a22003977 4500 001 1147229
005 20240909100731.5
006 m o d
007 cr bn ---uuuuu
008 250605s2022 xx obm 000 0 eng d
020 $a 9798841776529
035 $a (MiAaPQ)AAI29260735
035 $a AAI29260735
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Gong, Ze. $3 1472898
245 1 0 $a What Do You Want Me to Do? Addressing Model Differences for Human-Aware Decision-Making from a Learning Perspective.
264 0 $c 2022
300 $a 1 online resource (120 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: Dissertations Abstracts International, Volume: 84-02, Section: B.
500 $a Advisor: Zhang, Yu.
502 $a Thesis (Ph.D.)--Arizona State University, 2022.
504 $a Includes bibliographical references
520 $a As intelligent agents become pervasive in our lives, they are expected to not only achieve tasks alone but also engage in tasks with humans in the loop. In such cases, the human naturally forms an understanding of the agent, which affects his perception of the agent's behavior. However, such an understanding inevitably deviates from the ground truth due to reasons such as the human's lack of understanding of the domain or misunderstanding of the agent's capabilities. Such differences would result in an unmatched expectation of the agent's behavior with the agent's optimal behavior, thereby biasing the human's assessment of the agent's performance. In this dissertation, I focus on when these differences are due to a biased belief about domain dynamics. I especially investigate the impact of such a biased belief on the agent's decision-making process in two different problem settings from a learning perspective. In the first setting, the agent is tasked to accomplish a task alone but must infer the human's objectives from the human's feedback on the agent's behavior in the environment. In such a case, the human biased feedback could mislead the agent to learn a reward function that results in a sub-optimal and, potentially, undesired policy. In the second setting, the agent must accomplish a task with a human observer. Given that the agent's optimal behavior may not match the human's expectation due to the biased belief, the agent's optimal behavior may be viewed as inexplicable, leading to degraded performance and loss of trust. Consequently, this dissertation proposes approaches that (1) endow the agent with the ability to be aware of the human's biased belief while inferring the human's objectives, thereby (2) neutralize the impact of the model differences in a reinforcement learning framework, and (3) behave explicably by reconciling the human's expectation and optimality during decision-making.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Computer engineering. $3 569006
650 4 $a Computer science. $3 573171
650 4 $a Information technology. $3 559429
650 4 $a Information science. $3 561178
653 $a Human aware
653 $a Decision making
653 $a Learning perspective
655 7 $a Electronic books. $2 local $3 554714
690 $a 0489
690 $a 0984
690 $a 0464
690 $a 0723
690 $a 0800
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Arizona State University. $b Computer Science. $3 845377
773 0 $t Dissertations Abstracts International $g 84-02B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29260735 $z click for full text (PQDT)