Testing Reinforcement Learning Explainability Methods in a Multi-Agent Cooperative Environment

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Testing Reinforcement Learning Explainability Methods in a Multi-Agent Cooperative Environment
Συγγραφείς: Domènech Vila, Marc, Gnatyshak, Dmitry, Tormos Llorente, Adrián, Álvarez Napagao, Sergio
Πηγή: UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
Frontiers in Artificial Intelligence and Applications
Frontiers in Artificial Intelligence and Applications-Artificial Intelligence Research and Development
Στοιχεία εκδότη: IOS Press, 2022.
Έτος έκδοσης: 2022
Θεματικοί όροι: Multiagent systems, Cooperative environments, Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Agents intel·ligents, Reinforcement learning, Explainable AI, Aprenentatge per reforç, Sistemes multiagent, 0202 electrical engineering, electronic engineering, information engineering, 02 engineering and technology, Policy graphs, Multi-agent reinforcement learning
Περιγραφή: 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.
Τύπος εγγράφου: Part of book or chapter of book
Conference object
Article
Περιγραφή αρχείου: application/pdf
DOI: 10.3233/faia220358
Rights: CC BY NC
Αριθμός Καταχώρησης: edsair.doi.dedup.....c35b83631c9c05e59f5d2a2ec93d2a6f
Βάση Δεδομένων: OpenAIRE