Constructing Symbolic Representations for High-Level Planning

被引：0

作者：

Konidaris, George ^{[1
]}

Kaelbling, Leslie Pack ^{[1
]}

Lozano-Perez, Tomas ^{[1
]}

机构：

[1] MIT, Comp Sci & Artificial Intelligence Lab, 32 Vassar St, Cambridge, MA 02139 USA

来源：

PROCEEDINGS OF THE TWENTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE | 2014年

基金：

美国国家科学基金会;

关键词：

MOTION;

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：

We consider the problem of constructing a symbolic description of a continuous, low-level environment for use in planning. We show that symbols that can represent the preconditions and effects of an agent's actions are both necessary and sufficient for high-level planning. This eliminates the symbol design problem when a representation must be constructed in advance, and in principle enables an agent to autonomously learn its own symbolic representations. The resulting representation can be converted into PDDL, a canonical high-level planning representation that enables very fast planning.

引用

页码：1932 / +

页数：9

共 50 条

[41] PRINCIPLES OF PLANNING TECHNICAL SYSTEMS WITH HIGH-LEVEL OF RELIABILITY
KAFAROV, VV
GRUHN, G
CHEMISCHE TECHNIK, 1980, 32 (09): : 490 - 490
[42] HIGH-LEVEL MANPOWER PLANNING - ANALYSIS OF CZECHOSLOVAK EXPERIENCE
SOKOL, M
INTERNATIONAL LABOUR REVIEW, 1967, 95 (1-2) : 27 - 48
[43] Constructing SCORM compliant course based on high-level Petri nets
Su, JM
Tseng, SS
Chen, CY
Weng, JF
Tsai, WN
COMPUTER STANDARDS & INTERFACES, 2006, 28 (03) : 336 - 355
[44] Learning Symbolic Representations for Planning with Parameterized Skills
Ames, Barrett
Thackston, Allison
Konidaris, George
2018 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2018, : 526 - 533
[45] Developing high-level representations of video clips using video trails
Kobla, V
Doermann, D
Faloutsos, C
STORAGE AND RETRIEVAL FOR IMAGE AND VIDEO DATABASES VI, 1997, 3312 : 81 - 92
[46] Recovery of high-level intermediate representations of algorithms from binary code
Bugerya, Alexander Borisovich
Kulagin, Ivan Ivanovich
Padaryan, Vartan Andronikovich
Solovev, Mikhail Aleksandrovich
Tikhonov, Andrei Yur'evich
2019 IVANNIKOV MEMORIAL WORKSHOP (IVMEM 2019), 2019, : 57 - 63
[47] Canonical Representations for Direct Generation of Strategies in High-Level Petri Games
Gieseking, Manuel
Wuerdemann, Nick
APPLICATION AND THEORY OF PETRI NETS AND CONCURRENCY (PETRI NETS 2021), 2021, 12734 : 95 - 117
[48] Task alters category representations in prefrontal but not high-level visual cortex
Bugatus, Lior
Weiner, Kevin S.
Grill-Spector, Kalanit
NEUROIMAGE, 2017, 155 : 437 - 449
[49] A Symbolic Methodology for Formal Verification of High-level Data-Flow Synthesis
Yang, Zhi
Lv, Chao
Ma, Guangsheng
Shao, Jingbo
2008 9TH INTERNATIONAL CONFERENCE ON SOLID-STATE AND INTEGRATED-CIRCUIT TECHNOLOGY, VOLS 1-4, 2008, : 2345 - +
[50] Application of symbolic computer algebra in high-level data-flow synthesis
Peymandoust, A
De Micheli, G
IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2003, 22 (09) : 1154 - 1165

← 1 2 3 4 5 →