| Title: |
Testing reinforcement learning explainability methods in a multi-agent cooperative environment |
| Authors: |
Domènech Vila, Marc; Gnatyshak, Dmitry; Tormos Llorente, Adrián; Álvarez Napagao, Sergio |
| Contributors: |
Universitat Politècnica de Catalunya. Doctorat en Intel·ligència Artificial; Universitat Politècnica de Catalunya. Departament de Ciències de la Computació; Barcelona Supercomputing Center |
| Publisher Information: |
IOS Press |
| Publication Year: |
2022 |
| Collection: |
Universitat Politècnica de Catalunya, BarcelonaTech: UPCommons - Global access to UPC knowledge |
| Subject Terms: |
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Agents intel·ligents; Multiagent systems; Reinforcement learning; Explainable AI; Policy graphs; Multi-agent reinforcement learning; Cooperative environments; Sistemes multiagent; Aprenentatge per reforç |
| Description: |
The adoption of algorithms based on Artificial Intelligence (AI) has been rapidly increasing during the last years. However, some aspects of AI techniques are under heavy scrutiny. For instance, in many cases, it is not clear whether the decisions of an algorithm are well-informed and reliable. Having an answer to these concerns is crucial in many domains, such as those in were humans and intelligent agents must cooperate in a shared environment. In this paper, we introduce an application of an explainability method based on the creation of a Policy Graph (PG) based on discrete predicates that represent and explain a trained agent’s behaviour in a multi-agent cooperative environment. We also present a method to measure the similarity between the explanations obtained and the agent’s behaviour, by building an agent with a policy based on the PG and comparing the behaviour of the two agents. ; This work has been partially supported by the H2020 knowlEdge European project (Grant agreement ID: 957331). ; Peer Reviewed ; Postprint (published version) |
| Document Type: |
conference object |
| File Description: |
10 p.; application/pdf |
| Language: |
English |
| Relation: |
https://ebooks.iospress.nl/volumearticle/61264; info:eu-repo/grantAgreement/EC/H2020/957331/EU/Towards AI powered manufacturing services, processes, and products in an edge-to-cloud-knowlEdge continuum for humans [in-the-loop]/knowlEdge; https://hdl.handle.net/2117/375993 |
| DOI: |
10.3233/FAIA220358 |
| Availability: |
https://hdl.handle.net/2117/375993; https://doi.org/10.3233/FAIA220358 |
| Rights: |
http://creativecommons.org/licenses/by-nc/4.0/ ; Open Access ; Attribution-NonCommercial 4.0 International |
| Accession Number: |
edsbas.16320C10 |
| Database: |
BASE |