서브메뉴
검색
Leveraging Compositional Structure for Reinforcement Learning and Sequential Decision Making Problems
Leveraging Compositional Structure for Reinforcement Learning and Sequential Decision Making Problems
Detailed Information
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260202103648
- ISBN
- 9798314875445
- DDC
- 004
- 저자명
- Liu, Anthony Z.
- 서명/저자
- Leveraging Compositional Structure for Reinforcement Learning and Sequential Decision Making Problems
- 발행사항
- [Sl] : University of Michigan, 2025
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2025
- 형태사항
- 149 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 86-11, Section: A.
- 주기사항
- Advisor: Lee, Honglak.
- 학위논문주기
- Thesis (Ph.D.)--University of Michigan, 2025.
- 초록/해제
- 요약Deep Learning approaches have made tremendous progress toward solving reinforcement learning and sequential decision-making problems. However, current approaches still struggle with long-horizon tasks that require strong generalization. These are tasks that an agent must solve using many actions and may have situations where the agent must generalize its actions from prior experience. A dominant approach is to solve these tasks in a hierarchical manner: a high-level agent decomposes a task into multiple "subtasks" to be individually solved by a low-level agent, which specializes in solving these subtasks. The effectiveness of this approach is enhanced by identifying and utilizing the inherent compositional structures of tasks, which enable more efficient learning and broader generalization.This dissertation introduces novel methodologies that build on task compositionality to address these challenges. Key contributions include: (1) Higher-Order Skill Learning: A hierarchical reinforcement learning framework is proposed, enabling low-level policies to optimize for sequences of subtasks rather than individual ones, resulting in improved efficiency and performance. (2) Parameterized Task Structures: Introducing parameterized subtask graphs to model tasks with compositional structures, enhancing both the efficiency of task inference and generalization to unseen entities. In addition, contributions that show compositional structure can be used through language and large language models (LLMs): (3) Integrating Multimodal Observations in Language Models: Demonstrating that visual observations can be embedded as input tokens for large language models (LLMs), achieving state-of-the-art performance in visually grounded planning tasks. (4) Skill Abstractions for LLM Planning: Highlighting the benefits of providing LLMs with structured descriptions of subtasks, or skills, to improve planning and reasoning capabilities. (5) Code-Augmented Planning: Proposing a method where LLMs use control flow constructs to generate and execute code for solving complex planning tasks, significantly improving task performance.Collectively, these approaches showcase how leveraging task compositionality through hierarchical structures and language from LLMs can improve reinforcement learning and sequential decision-making frameworks.
- 일반주제명
- Computer science
- 일반주제명
- Computer engineering
- 일반주제명
- Information science
- 기타저자
- University of Michigan Computer Science & Engineering
- 기본자료저록
- Dissertations Abstracts International. 86-11A.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260126s2025 us c eng d■001000017358126
■00520260202103648
■006m o d
■007cr#unu||||||||
■020 ▼a9798314875445
■035 ▼a(MiAaPQ)AAI32092652
■035 ▼a(MiAaPQ)umichrackham005989
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a004
■1001 ▼aLiu, Anthony Z.
■24510▼aLeveraging Compositional Structure for Reinforcement Learning and Sequential Decision Making Problems
■260 ▼a[Sl]▼bUniversity of Michigan▼c2025
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2025
■300 ▼a149 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 86-11, Section: A.
■500 ▼aAdvisor: Lee, Honglak.
■5021 ▼aThesis (Ph.D.)--University of Michigan, 2025.
■520 ▼aDeep Learning approaches have made tremendous progress toward solving reinforcement learning and sequential decision-making problems. However, current approaches still struggle with long-horizon tasks that require strong generalization. These are tasks that an agent must solve using many actions and may have situations where the agent must generalize its actions from prior experience. A dominant approach is to solve these tasks in a hierarchical manner: a high-level agent decomposes a task into multiple "subtasks" to be individually solved by a low-level agent, which specializes in solving these subtasks. The effectiveness of this approach is enhanced by identifying and utilizing the inherent compositional structures of tasks, which enable more efficient learning and broader generalization.This dissertation introduces novel methodologies that build on task compositionality to address these challenges. Key contributions include: (1) Higher-Order Skill Learning: A hierarchical reinforcement learning framework is proposed, enabling low-level policies to optimize for sequences of subtasks rather than individual ones, resulting in improved efficiency and performance. (2) Parameterized Task Structures: Introducing parameterized subtask graphs to model tasks with compositional structures, enhancing both the efficiency of task inference and generalization to unseen entities. In addition, contributions that show compositional structure can be used through language and large language models (LLMs): (3) Integrating Multimodal Observations in Language Models: Demonstrating that visual observations can be embedded as input tokens for large language models (LLMs), achieving state-of-the-art performance in visually grounded planning tasks. (4) Skill Abstractions for LLM Planning: Highlighting the benefits of providing LLMs with structured descriptions of subtasks, or skills, to improve planning and reasoning capabilities. (5) Code-Augmented Planning: Proposing a method where LLMs use control flow constructs to generate and execute code for solving complex planning tasks, significantly improving task performance.Collectively, these approaches showcase how leveraging task compositionality through hierarchical structures and language from LLMs can improve reinforcement learning and sequential decision-making frameworks.
■590 ▼aSchool code: 0127.
■650 4▼aComputer science
■650 4▼aComputer engineering
■650 4▼aInformation science
■653 ▼aHierarchical reinforcement learning
■653 ▼aTask decomposition
■653 ▼aLarge language models
■653 ▼aTask generalization
■653 ▼aDecision-making problems
■690 ▼a0984
■690 ▼a0464
■690 ▼a0723
■71020▼aUniversity of Michigan▼bComputer Science & Engineering.
■7730 ▼tDissertations Abstracts International▼g86-11A.
■790 ▼a0127
■791 ▼aPh.D.
■792 ▼a2025
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17358126▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
Preview
Export
ChatGPT Discussion
AI Recommended Related Books
Info Détail de la recherche.
- Réservation
- n'existe pas
- My Folder
- Demande Première utilisation
- Non-Book Loan Application
- Nighttime Book Loan Application
Available after logging in.


