ADAM: A Prototype of Hierarchical Neuro-Symbolic AGI

被引：1
|
作者：
Shumsky, Sergey [1 ]
Baskov, Oleg [1 ]
机构：
[1] Moscow Inst Phys & Technol, Dolgoprudnyi 141701, Russia
来源：
ARTIFICIAL GENERAL INTELLIGENCE, AGI 2023 | 2023年 / 13921卷
关键词：
Artificial General Intelligence; Hierarchical reinforcement learning; Neuro-symbolic architecture; MODEL;
D O I：
10.1007/978-3-031-33469-6_26
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Intelligent agents are characterized primarily by their farsighted expedient behavior. We present a working prototype of an intelligent agent (ADAM) based on a novel hierarchical neuro-symbolic architecture (Deep Control) for deep reinforcement learning with a potentially unlimited planning horizon. The control parameters form a hierarchy of formal languages, where higher-level alphabets contain the semantic meanings of lower-level vocabularies.
引用
收藏
页码：255 / 264
页数：10
相关论文
共 20 条
  • [1] Detect, Understand, Act: A Neuro-symbolic Hierarchical Reinforcement Learning Framework
    Ludovico Mitchener
    David Tuckey
    Matthew Crosby
    Alessandra Russo
    Machine Learning, 2022, 111 : 1523 - 1549
  • [2] Detect, Understand, Act: A Neuro-symbolic Hierarchical Reinforcement Learning Framework
    Mitchener, Ludovico
    Tuckey, David
    Crosby, Matthew
    Russo, Alessandra
    MACHINE LEARNING, 2022, 111 (04) : 1523 - 1549
  • [3] NeST: The neuro-symbolic transpiler
    Pfanschilling, Viktor
    Shindo, Hikaru
    Dhami, Devendra Singh
    Kersting, Kristian
    INTERNATIONAL JOURNAL OF APPROXIMATE REASONING, 2025, 179
  • [4] One Possibility of a Neuro-Symbolic Integration
    Samsonovich, Alexei, V
    BIOLOGICALLY INSPIRED COGNITIVE ARCHITECTURES 2021, 2022, 1032 : 428 - 437
  • [5] A probabilistic approximate logic for neuro-symbolic learning and reasoning
    Stehr, Mark-Oliver
    Kim, Minyoung
    Talcott, Carolyn L.
    JOURNAL OF LOGICAL AND ALGEBRAIC METHODS IN PROGRAMMING, 2022, 124
  • [6] Neuro-Symbolic Architecture for Experiential Learning in Discrete and Functional Environments
    Kolonin, Anton
    ARTIFICIAL GENERAL INTELLIGENCE, AGI 2021, 2022, 13154 : 106 - 115
  • [7] Towards bridging the neuro-symbolic gap: deep deductive reasoners
    Ebrahimi, Monireh
    Eberhart, Aaron
    Bianchi, Federico
    Hitzler, Pascal
    APPLIED INTELLIGENCE, 2021, 51 (09) : 6326 - 6348
  • [8] Neuro-Symbolic Hybrid Systems for Industry 4.0: A Systematic Mapping Study
    Sitton, Ines
    Alonso, Ricardo S.
    Hernandez-Nieves, Elena
    Rodriguez-Gonzalez, Sara
    Rivas, Alberto
    KNOWLEDGE MANAGEMENT IN ORGANIZATIONS, KMO 2019, 2019, 1027 : 455 - 465
  • [9] DeepProbCEP: A neuro-symbolic approach for complex event processing in adversarial settings
    Vilamala, Marc Roig
    Xing, Tianwei
    Taylor, Harrison
    Garcia, Luis
    Srivastava, Mani
    Kaplan, Lance
    Preece, Alun
    Kimmig, Angelika
    Cerutti, Federico
    EXPERT SYSTEMS WITH APPLICATIONS, 2023, 215
  • [10] Crowd evacuation with human-level intelligence via neuro-symbolic approach
    Bahamid, Alala
    Ibrahim, Azhar Mohd
    Shafie, Amir Akramin
    ADVANCED ENGINEERING INFORMATICS, 2024, 60
12