Forward Search Value Iteration For POMDPs

被引：0

作者：

Shani, Guy ^{[1
]}

Brafman, Ronen I. ^{[1
]}

Shimony, Solomon E. ^{[1
]}

机构：

[1] Ben Gurion Univ Negev, Dept Comp Sci, Beer Sheva, Israel

来源：

20TH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE | 2007年

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Recent scaling up of POMDP solvers towards realistic applications is largely due to point-based methods which quickly converge to an approximate solution for medium-sized problems. Of this family HSVI, which uses trial-based asynchronous value iteration, can handle the largest domains. In this paper we suggest a new algorithm, FSVI, that uses the underlying MDP to traverse the belief space towards rewards, finding sequences of useful backups, and show how it scales up better than HSVI on larger benchmarks.

引用

页码：2619 / 2624

页数：6

共 50 条

[41] Sound Value Iteration
Quatmann, Tim
Katoen, Joost-Pieter
COMPUTER AIDED VERIFICATION (CAV 2018), PT I, 2018, 10981 : 643 - 661
[42] The Cross-Entropy Method for Policy Search in Decentralized POMDPs
Oliehoek, Frans A.
Kooij, Julian F. P.
Vlassis, Nikos
INFORMATICA-JOURNAL OF COMPUTING AND INFORMATICS, 2008, 32 (04): : 341 - 357
[43] A note on forward iteration of inner functions
Ferreira, Gustavo R.
BULLETIN OF THE LONDON MATHEMATICAL SOCIETY, 2023, 55 (03) : 1143 - 1153
[44] Doubly-Asynchronous Value Iteration: Making Value Iteration Asynchronous in Actions
Tian, Tian
Young, Kenny
Sutton, Richard S.
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35, NEURIPS 2022, 2022,
[45] PLEASE: Palm Leaf Search for POMDPs with Large Observation Spaces
Zhang, Zongzhang
Hsu, David
Lee, Wee Sun
Lim, Zhan Wei
Bai, Aijun
PROCEEDINGS OF THE TWENTY-FIFTH INTERNATIONAL CONFERENCE ON AUTOMATED PLANNING AND SCHEDULING, 2015, : 249 - 257
[46] The forward search
Atkinson, A
COMPSTAT 2002: PROCEEDINGS IN COMPUTATIONAL STATISTICS, 2002, : 587 - 592
[47] Multi-Object Search using Object-Oriented POMDPs
Wandzel, Arthur
Oh, Yoonseon
Fishman, Michael
Kumar, Nishanth
Wong, Lawson L. S.
Tellex, Stefanie
2019 INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2019, : 7194 - 7200
[48] Sparse Tree Search Optimality Guarantees in POMDPs with Continuous Observation Spaces
Lim, Michael H.
Tomlin, Claire J.
Sunberg, Zachary N.
PROCEEDINGS OF THE TWENTY-NINTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2020, : 4135 - 4142
[49] Optimal and approximate Q-value functions for decentralized POMDPs
Oliehoek, Frans A.
Spaan, Matthijs T. J.
Vlassis, Nikos
JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH, 2008, 32 : 289 - 353
[50] ρ-POMDPs have Lipschitz-Continuous ε-Optimal Value Functions
Fehr, Mathieu
Buffett, Olivier
Thomas, Vincent
Dibangoye, Junes
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), 2018, 31

← 1 2 3 4 5 →