Learnability with PAC Semantics for Multi-agent Beliefs

Ionela G. Mocanu; Vaishak Belle; Brendan Juba

Learnability with PAC Semantics for Multi-agent Beliefs

Ionela G. Mocanu, Vaishak Belle, Brendan Juba

Department of Computer Science & Engineering

Research output: Contribution to journal › Conference article › peer-review

Abstract

This work proposes a new technical foundation for demonstrating Probably Approximately Correct (PAC) learning with multiagent epistemic logics, using implicit learning to incorporate observations into the background knowledge. We explore the sample complexity and the circumstances in which the algorithm can be made efficient.

Original language	English
Pages (from-to)	2604-2606
Number of pages	3
Journal	Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
Volume	2023-May
State	Published - 2023
Event	22nd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2023 - London, United Kingdom Duration: May 29 2023 → Jun 2 2023

Keywords

Knowledge Acquisition
Multi-Agent Logics
Only-Knowing

Cite this

@article{98f948271c8c4bd6b50c786aeaf7567e,

title = "Learnability with PAC Semantics for Multi-agent Beliefs",

abstract = "This work proposes a new technical foundation for demonstrating Probably Approximately Correct (PAC) learning with multiagent epistemic logics, using implicit learning to incorporate observations into the background knowledge. We explore the sample complexity and the circumstances in which the algorithm can be made efficient.",

keywords = "Knowledge Acquisition, Multi-Agent Logics, Only-Knowing",

author = "Mocanu, {Ionela G.} and Vaishak Belle and Brendan Juba",

note = "Publisher Copyright: {\textcopyright} 2023 International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org). All rights reserved.; 22nd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2023 ; Conference date: 29-05-2023 Through 02-06-2023",

year = "2023",

language = "English",

volume = "2023-May",

pages = "2604--2606",

journal = "Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS",

issn = "1548-8403",

}

TY - JOUR

T1 - Learnability with PAC Semantics for Multi-agent Beliefs

AU - Mocanu, Ionela G.

AU - Belle, Vaishak

AU - Juba, Brendan

PY - 2023

Y1 - 2023

N2 - This work proposes a new technical foundation for demonstrating Probably Approximately Correct (PAC) learning with multiagent epistemic logics, using implicit learning to incorporate observations into the background knowledge. We explore the sample complexity and the circumstances in which the algorithm can be made efficient.

AB - This work proposes a new technical foundation for demonstrating Probably Approximately Correct (PAC) learning with multiagent epistemic logics, using implicit learning to incorporate observations into the background knowledge. We explore the sample complexity and the circumstances in which the algorithm can be made efficient.

KW - Knowledge Acquisition

KW - Multi-Agent Logics

KW - Only-Knowing

UR - http://www.scopus.com/inward/record.url?scp=85171254392&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85171254392

SN - 1548-8403

VL - 2023-May

SP - 2604

EP - 2606

JO - Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS

JF - Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS

T2 - 22nd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2023

Y2 - 29 May 2023 through 2 June 2023

ER -

Learnability with PAC Semantics for Multi-agent Beliefs

Abstract

Keywords

Other files and links

Fingerprint

Cite this