Explaining the Behaviour of Reinforcement Learning Agents in a Multi-Agent Cooperative Environment Using Policy Graphs

M Domenech i Vila, D Gnatyshak, A Tormos… - Electronics, 2024 - mdpi.com
The adoption of algorithms based on Artificial Intelligence (AI) has been rapidly increasing
during the last few years. However, some aspects of AI techniques are under heavy scrutiny …

[PDF][PDF] Toward Explainable Agent Behaviour

V Gimenez-Abalos - Proceedings of the 23rd International Conference …, 2024 - ifaamas.org
Agents are a special kind of AI-based software in that they interact in complex environments
and have increased potential for emergent behaviour, even in isolation. Explaining such …

pgeon applied to Overcooked-AI to explain agents' behaviour

A Tormos Llorente, V Giménez Ábalos… - … '24: Proceedings of …, 2024 - upcommons.upc.edu
Policy Graphs (PGs) are a method for representing the behaviour of opaque agents by
observing them in the environment and producing graphs where the state and action spaces …

Extracting explanations about cooperation in a multi-agent reinforcement learning scenario

MA Balaguera Lizcano - 2023 - upcommons.upc.edu
Reinforcement learning is a Machine Learning technique where an agent learns how to
interact in an dynamic environment by performing actions and getting rewards or …

Metode d'explicabilitat per Aprenentatge Per Reforç Multiagent en presència de comunicació

A García Belmonte - 2024 - upcommons.upc.edu
Les tècniques d'aprenentatge per reforç creen models de caixa negra impredictibles,
afectant a la seguretat/confiança en els agents. Es proposa buscar i/o dissenyar un entorn …

[PDF][PDF] pgeon applied to Overcooked-AI to explain agents' behaviour

A Tormos, V Gimenez-Abalos, J Vázquez-Salceda… - ifaamas.org
ABSTRACT Policy Graphs (PGs) are a method for representing the behaviour of opaque
agents by observing them in the environment and producing graphs where the state and …