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 50 条
  • [41] Learning Neuro-Symbolic Skills for Bilevel Planning
    Silver, Tom
    Athalye, Ashay
    Tenenbaum, Joshua B.
    Lozano-Perez, Tomas
    Kaelbling, Leslie Pack
    CONFERENCE ON ROBOT LEARNING, VOL 205, 2022, 205 : 701 - 714
  • [42] Semantic Probabilistic Layers for Neuro-Symbolic Learning
    Ahmed, Kareem
    Teso, Stefano
    Chang, Kai-Wei
    Van den Broeck, Guy
    Vergari, Antonio
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35, NEURIPS 2022, 2022,
  • [43] Clauses Representation Comparison in Neuro-Symbolic Integration
    Sathasivam, Saratha
    WORLD CONGRESS ON ENGINEERING, WCE 2010, VOL I, 2010, : 34 - 37
  • [44] From Statistical Relational to Neuro-Symbolic Artificial Intelligence
    Marra, Giuseppe
    THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 20, 2024, : 22678 - 22678
  • [45] Neuro-symbolic model for cantilever beams damage detection
    Onchis, Darian M.
    Gillich, Gilbert-Rainer
    Hogea, Eduard
    Tufisi, Cristian
    COMPUTERS IN INDUSTRY, 2023, 151
  • [46] From Probabilistic Logics to Neuro-Symbolic Artificial Intelligence
    De Readt, Luc
    ELECTRONIC PROCEEDINGS IN THEORETICAL COMPUTER SCIENCE, 2020, (325):
  • [47] APPLYING DIFFERENT LEARNING RULES IN NEURO-SYMBOLIC INTEGRATION
    Sathasivam, Saratha
    MATERIALS SCIENCE AND INFORMATION TECHNOLOGY, PTS 1-8, 2012, 433-440 : 716 - 720
  • [48] A Neuro-Symbolic ASP Pipeline for Visual Question Answering
    Eiter, Thomas
    Higuera, Nelson
    Oetsch, Johannes
    Pritz, Michael
    THEORY AND PRACTICE OF LOGIC PROGRAMMING, 2022, 22 (05) : 739 - 754
  • [49] Learning Neuro-Symbolic Abstractions for Robot Planning and Learning
    Shah, Naman
    THIRTY-EIGTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 21, 2024, : 23417 - 23418
  • [50] A Neuro-Symbolic Approach for Enhanced Human Motion Prediction
    Mghames, Sariah
    Castri, Luca
    Hanheide, Marc
    Bellotto, Nicola
    2023 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN, 2023,
12345