國立虎尾科技大學 |

Reinforcement Learning for Robotic Tasks : = Analyzing and Understanding the Learning Process Using Explainable Artificial Intelligence Methods.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Reinforcement Learning for Robotic Tasks :/
其他題名:	Analyzing and Understanding the Learning Process Using Explainable Artificial Intelligence Methods.
作者:	Campana, Brian Joseph.
面頁冊數:	1 online resource (71 pages)
附註:	Source: Masters Abstracts International, Volume: 85-12.
Contained By:	Masters Abstracts International85-12.
標題:	Information technology. -
電子資源:	click for full text (PQDT)
ISBN:	9798382953243

Reinforcement Learning for Robotic Tasks : = Analyzing and Understanding the Learning Process Using Explainable Artificial Intelligence Methods.
Campana, Brian Joseph.

Reinforcement Learning for Robotic Tasks :Analyzing and Understanding the Learning Process Using Explainable Artificial Intelligence Methods. - 1 online resource (71 pages)

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

Thesis (M.Sc.C.S.)--Rowan University, 2024.

Includes bibliographical references

As deep reinforcement learning (RL) models gain traction across more industries, there is a growing need for reliable agent-explanation techniques to understand these models. Researchers have developed explainable artificial intelligence (XAI) methods to help understand these 'black boxes'. While these models have been tested on many supervised learning tasks, there is a lack of examination of how these well these methods can explain hard reinforcement learning problems like robotic control. The sequential nature of learning RL policies and testing episodes create fundamentally different policies over time compared to more traditional supervised learning models.In this thesis, two important questions are explored: (1) How well do modern Shapley value based explanation techniques help understand the rationale behind actions made by robotic RL actors? (2) Can these explanations help demystify the RL training loop by estimating the predictive weight of different features throughout training epochs? Through extensive empirical experiments on multiple robotic environments and output analysis, we obtain the following observations:1. Modern Shapley value explanation techniques often require a significant amount of extra data analysis to comprehend the logic behind trained policies.2. Important, predictive features are found and ranked highly very early in mid-training epochs before the optimal policy is found.

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

Mode of access: World Wide Web

ISBN: 9798382953243Subjects--Topical Terms:

559429
Information technology.
Subjects--Index Terms:

Explainable artificial intelligenceIndex Terms--Genre/Form:

554714
Electronic books.

Reinforcement Learning for Robotic Tasks : = Analyzing and Understanding the Learning Process Using Explainable Artificial Intelligence Methods.
LDR:02851ntm a22003977 4500 001 1150216
005 20241022111616.5
006 m o d
007 cr bn ---uuuuu
008 250605s2024 xx obm 000 0 eng d
020 $a 9798382953243
035 $a (MiAaPQ)AAI31331213
035 $a AAI31331213
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Campana, Brian Joseph. $3 1476658
245 1 0 $a Reinforcement Learning for Robotic Tasks : $b Analyzing and Understanding the Learning Process Using Explainable Artificial Intelligence Methods.
264 0 $c 2024
300 $a 1 online resource (71 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: Ho, Shen-Shyang.
502 $a Thesis (M.Sc.C.S.)--Rowan University, 2024.
504 $a Includes bibliographical references
520 $a As deep reinforcement learning (RL) models gain traction across more industries, there is a growing need for reliable agent-explanation techniques to understand these models. Researchers have developed explainable artificial intelligence (XAI) methods to help understand these 'black boxes'. While these models have been tested on many supervised learning tasks, there is a lack of examination of how these well these methods can explain hard reinforcement learning problems like robotic control. The sequential nature of learning RL policies and testing episodes create fundamentally different policies over time compared to more traditional supervised learning models.In this thesis, two important questions are explored: (1) How well do modern Shapley value based explanation techniques help understand the rationale behind actions made by robotic RL actors? (2) Can these explanations help demystify the RL training loop by estimating the predictive weight of different features throughout training epochs? Through extensive empirical experiments on multiple robotic environments and output analysis, we obtain the following observations:1. Modern Shapley value explanation techniques often require a significant amount of extra data analysis to comprehend the logic behind trained policies.2. Important, predictive features are found and ranked highly very early in mid-training epochs before the optimal policy is found.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Information technology. $3 559429
650 4 $a Robotics. $3 561941
650 4 $a Computer science. $3 573171
653 $a Explainable artificial intelligence
653 $a Machine learning
653 $a Reinforcement learning
653 $a Shapley values
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
690 $a 0800
690 $a 0771
690 $a 0489
710 2 $a Rowan University. $b Computer Science. $3 1476659
710 2 $a ProQuest Information and Learning Co. $3 1178819
773 0 $t Masters Abstracts International $g 85-12.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31331213 $z click for full text (PQDT)