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

Machine Learning for Decision Making...

Lu, Hao.

FindBook

Google Book

Amazon

博客來

Machine Learning for Decision Making: Applications to Off-Policy Learning and Combinatorial Optimization.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Machine Learning for Decision Making: Applications to Off-Policy Learning and Combinatorial Optimization./
作者:	Lu, Hao.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	144 p.
附註:	Source: Dissertations Abstracts International, Volume: 82-12, Section: B.
Contained By:	Dissertations Abstracts International82-12B.
標題:	Operations research. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28494717
ISBN:	9798515255930

Machine Learning for Decision Making: Applications to Off-Policy Learning and Combinatorial Optimization.
Lu, Hao.

Machine Learning for Decision Making: Applications to Off-Policy Learning and Combinatorial Optimization. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 144 p.

Source: Dissertations Abstracts International, Volume: 82-12, Section: B.

Thesis (Ph.D.)--Princeton University, 2021.

This item must not be sold to any third party vendors.

In this thesis, we discuss machine learning methods for decision-making problems in off-policy learning and combinatorial optimization.We start with off-policy learning problems, specifically in the scenario of healthcare. In the first part, we model the clinical pathway optimization for knee replacement. Based on episodic claims from previous cases, we view pathway optimization as an intelligence crowdsourcing problem and learn the optimal decision policy from data by imitating the best expert at every intermediate state. We develop a reinforcement learning-based pipeline that uses value iteration, state compression, aggregation learning, and kernel representation to predict the best treatment policy. In the second part, we adopt the bootstrapping fitted Q-evaluation (FQE) algorithm for policy evaluation with off-policy data in sepsis treatment. Our method achieves reliable point estimates and confidence regions with neural network function approximators.We then explore combinatorial optimization problems from both empirical and theoretical perspectives. First, we study the empirical capacitated vehicle routing problem (CVRP) with a reinforcement learning approach. We present Learn to Improve (L2I), the first learning-based approach for CVRP that is efficient in solving speed and at the same time outperforms OR methods. Then we take a theoretical point of view in analyzing the computational-statistical gap of certain combinatorial problems. More specifically, we look at the hypothesis testing of inferring the existence of combinatorial structures in undirected graphical models. We quantify the minimum computational complexity required to attain the information-theoretic limits based on an oracle computational model, which is determined by two intrinsic quantities of the graph.

ISBN: 9798515255930Subjects--Topical Terms:

547123
Operations research.
Subjects--Index Terms:

Machine learning

Machine Learning for Decision Making: Applications to Off-Policy Learning and Combinatorial Optimization.
LDR:02953nmm a2200361 4500 001 2282081
005 20210927083536.5
008 220723s2021 ||||||||||||||||| ||eng d
020 $a 9798515255930
035 $a (MiAaPQ)AAI28494717
035 $a AAI28494717
040 $a MiAaPQ $c MiAaPQ
100 1 $a Lu, Hao. $3 3171765
245 1 0 $a Machine Learning for Decision Making: Applications to Off-Policy Learning and Combinatorial Optimization.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 144 p.
500 $a Source: Dissertations Abstracts International, Volume: 82-12, Section: B.
500 $a Advisor: Wang, Mengdi.
502 $a Thesis (Ph.D.)--Princeton University, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a In this thesis, we discuss machine learning methods for decision-making problems in off-policy learning and combinatorial optimization.We start with off-policy learning problems, specifically in the scenario of healthcare. In the first part, we model the clinical pathway optimization for knee replacement. Based on episodic claims from previous cases, we view pathway optimization as an intelligence crowdsourcing problem and learn the optimal decision policy from data by imitating the best expert at every intermediate state. We develop a reinforcement learning-based pipeline that uses value iteration, state compression, aggregation learning, and kernel representation to predict the best treatment policy. In the second part, we adopt the bootstrapping fitted Q-evaluation (FQE) algorithm for policy evaluation with off-policy data in sepsis treatment. Our method achieves reliable point estimates and confidence regions with neural network function approximators.We then explore combinatorial optimization problems from both empirical and theoretical perspectives. First, we study the empirical capacitated vehicle routing problem (CVRP) with a reinforcement learning approach. We present Learn to Improve (L2I), the first learning-based approach for CVRP that is efficient in solving speed and at the same time outperforms OR methods. Then we take a theoretical point of view in analyzing the computational-statistical gap of certain combinatorial problems. More specifically, we look at the hypothesis testing of inferring the existence of combinatorial structures in undirected graphical models. We quantify the minimum computational complexity required to attain the information-theoretic limits based on an oracle computational model, which is determined by two intrinsic quantities of the graph.
590 $a School code: 0181.
650 4 $a Operations research. $3 547123
650 4 $a Artificial intelligence. $3 516317
650 4 $a Computer science. $3 523869
650 4 $a Information science. $3 554358
653 $a Machine learning
653 $a Decision making
653 $a Off-policy learning
690 $a 0796
690 $a 0800
690 $a 0984
690 $a 0723
710 2 $a Princeton University. $b Operations Research and Financial Engineering. $3 2096743
773 0 $t Dissertations Abstracts International $g 82-12B.
790 $a 0181
791 $a Ph.D.
792 $a 2021
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28494717