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

Enhancing Policy Optimization for Im...

Rahman, Md Masudur,

FindBook

Google Book

Amazon

博客來

Enhancing Policy Optimization for Improved Sample Efficiency and Generalization in Deep Reinforcement Learning /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Enhancing Policy Optimization for Improved Sample Efficiency and Generalization in Deep Reinforcement Learning // Md Masudur Rahman.
作者:	Rahman, Md Masudur,
面頁冊數:	1 electronic resource (197 pages)
附註:	Source: Dissertations Abstracts International, Volume: 86-05, Section: B.
Contained By:	Dissertations Abstracts International86-05B.
標題:	Robots. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31732969
ISBN:	9798346584544

Enhancing Policy Optimization for Improved Sample Efficiency and Generalization in Deep Reinforcement Learning /
Rahman, Md Masudur,

Enhancing Policy Optimization for Improved Sample Efficiency and Generalization in Deep Reinforcement Learning /Md Masudur Rahman. - 1 electronic resource (197 pages)

Source: Dissertations Abstracts International, Volume: 86-05, Section: B.

The field of reinforcement learning has made significant progress in recent years, with deep reinforcement learning (RL) being a major contributor. However, there are still challenges associated with the effective training of RL algorithms, particularly with respect to sample efficiency and generalization. This thesis aims to address these challenges by developing RL algorithms capable of generalizing to unseen environments and adapting to dynamic conditions, thereby expanding the practical applicability of RL in real-world tasks. The first contribution of this thesis is the development of novel policy optimization techniques that enhance the generalization capabilities of RL agents. These techniques include the Thinker method, which employs style transfer to diversify observation trajectories, and Bootstrap Advantage Estimation, which improves policy and value function learning through augmented data. These methods have demonstrated superior performance in standard benchmarks, outperforming existing data augmentation and policy optimization techniques. Additionally, this thesis introduces Robust Policy Optimization, a method that enhances exploration in policy gradient-based RL by perturbing action distributions. This method addresses the limitations of traditional methods, such as entropy collapse and primacy bias, resulting in improved sample efficiency and adaptability in continuous action spaces. The thesis further explores the potential of natural language descriptions as an alternative to image-based state representations in RL. This approach enhances interpretability and generalization in tasks involving complex visual observations by leveraging large language models. Furthermore, this work contributes to the field of semi-autonomous teleoperated robotic surgery by developing systems capable of performing complex surgical tasks remotely, even under challenging conditions such as communication delays and data scarcity. The creation of the DESK dataset supports knowledge transfer across different robotic platforms, further enhancing the capabilities of these systems. Overall, the advancements presented in this thesis represent significant steps toward developing more robust, adaptable, and efficient autonomous agents. These contributions have broad implications for various real-world applications, including autonomous systems, robotics, and safety-critical tasks such as medical surgery.

English

ISBN: 9798346584544Subjects--Topical Terms:

529507
Robots.

Enhancing Policy Optimization for Improved Sample Efficiency and Generalization in Deep Reinforcement Learning /
LDR:03762nmm a22003733i 4500 001 2435941
005 20251014050545.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798346584544
035 $a (MiAaPQD)AAI31732969
035 $a (MiAaPQD)Purdue27188148
035 $a AAI31732969
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Rahman, Md Masudur, $e author. $3 3826430
245 1 0 $a Enhancing Policy Optimization for Improved Sample Efficiency and Generalization in Deep Reinforcement Learning / $c Md Masudur Rahman.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (197 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: 86-05, Section: B.
500 $a Advisors: Xue, Yexiang Committee members: Bingham, Clifton W.; Wachs, Juan P.; Qureshi, Ah H.
502 $b Ph.D. $c Purdue University $d 2024.
520 $a The field of reinforcement learning has made significant progress in recent years, with deep reinforcement learning (RL) being a major contributor. However, there are still challenges associated with the effective training of RL algorithms, particularly with respect to sample efficiency and generalization. This thesis aims to address these challenges by developing RL algorithms capable of generalizing to unseen environments and adapting to dynamic conditions, thereby expanding the practical applicability of RL in real-world tasks. The first contribution of this thesis is the development of novel policy optimization techniques that enhance the generalization capabilities of RL agents. These techniques include the Thinker method, which employs style transfer to diversify observation trajectories, and Bootstrap Advantage Estimation, which improves policy and value function learning through augmented data. These methods have demonstrated superior performance in standard benchmarks, outperforming existing data augmentation and policy optimization techniques. Additionally, this thesis introduces Robust Policy Optimization, a method that enhances exploration in policy gradient-based RL by perturbing action distributions. This method addresses the limitations of traditional methods, such as entropy collapse and primacy bias, resulting in improved sample efficiency and adaptability in continuous action spaces. The thesis further explores the potential of natural language descriptions as an alternative to image-based state representations in RL. This approach enhances interpretability and generalization in tasks involving complex visual observations by leveraging large language models. Furthermore, this work contributes to the field of semi-autonomous teleoperated robotic surgery by developing systems capable of performing complex surgical tasks remotely, even under challenging conditions such as communication delays and data scarcity. The creation of the DESK dataset supports knowledge transfer across different robotic platforms, further enhancing the capabilities of these systems. Overall, the advancements presented in this thesis represent significant steps toward developing more robust, adaptable, and efficient autonomous agents. These contributions have broad implications for various real-world applications, including autonomous systems, robotics, and safety-critical tasks such as medical surgery.
546 $a English
590 $a School code: 0183
650 4 $a Robots. $3 529507
650 4 $a Deep learning. $3 3554982
650 4 $a Entropy. $3 546219
650 4 $a Normal distribution. $3 3561025
650 4 $a Natural language. $3 3562052
650 4 $a Robotics. $3 519753
690 $a 0800
690 $a 0771
710 2 $a Purdue University. $e degree granting institution. $3 3759105
720 1 $a Xue, Yexiang $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-05B.
790 $a 0183
791 $a Ph.D.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31732969