---
title: "On the Learnability of Knowledge in Multi-Agent Logics"
authors:
  - "Ionela G Mocanu"
doi: "10.24963/ijcai.2021/685"
url: "https://ijcai.org/proceedings/2021/685"
pdf: "https://ijcai.org/proceedings/2021/0685.pdf"
venue: "Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"
year: 2021
pages: "4907-4908"
track: "Doctoral Consortium"
keywords:
  - "Knowledge Representation and Reasoning: Logics for Knowledge Representation"
  - "Agent-based and Multi-agent Systems: Multi-agent Learning"
  - "Knowledge Representation and Reasoning: Reasoning about Knowledge and Belief"
  - "Knowledge Representation and Reasoning: Knowledge Representation Languages"
---

# On the Learnability of Knowledge in Multi-Agent Logics

Ionela G Mocanu

*Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence*, pages 4907-4908. DOI: [10.24963/ijcai.2021/685](https://doi.org/10.24963/ijcai.2021/685)

## Abstract

Since knowledge engineering is an inherently challenging and somewhat unbounded task, machine learning has been widely proposed as an alternative. In real world scenarios, we often need to explicitly model multiple agents, where intelligent agents act towards achieving goals either by coordinating with the other agents or by overseeing the opponents moves, if in a competitive context. We consider the knowledge acquisition problem where agents have knowledge about the world and other agents and then acquire new knowledge (both about the world as well as other agents) in service of answering queries. We propose a model of implicit learning, or more generally, learning to reason, which bypasses the intractable step of producing an explicit representation of the learned knowledge. We show that polynomial-time learnability results can be obtained when limited to knowledge bases and observations consisting of conjunctions of modal literals.