Learnability with PAC Semantics for Multi-agent Beliefs

Ionela Mocanu, Brendan Juba, Vaishak Belle

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

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 languageEnglish
Title of host publicationProceedings of the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS)
Place of PublicationRichland, SC
PublisherInternational Foundation for Autonomous Agents and Multiagent Systems
Pages2604–2606
Number of pages3
ISBN (Electronic)9781450394321
DOIs
Publication statusPublished - 30 May 2023
EventThe 22nd International Conference on Autonomous Agents and Multiagent Systems, 2023 - London, United Kingdom
Duration: 29 May 20232 Jun 2023
Conference number: 22
https://aamas2023.soton.ac.uk/

Conference

ConferenceThe 22nd International Conference on Autonomous Agents and Multiagent Systems, 2023
Abbreviated titleAAMAS 2023
Country/TerritoryUnited Kingdom
CityLondon
Period29/05/232/06/23
Internet address

Fingerprint

Dive into the research topics of 'Learnability with PAC Semantics for Multi-agent Beliefs'. Together they form a unique fingerprint.

Cite this