Nieves Montes, a Ph.D. student at the Artificial Intelligence Research Institute in Barcelona, Spain, joins us. Her PhD research revolves around value-based reasoning in relation to norms. She shares her latest study, Combining theory of mind and abductive reasoning in agent‑oriented programming
Nieves gave an introduction to what multiagent systems are and how they fit into other machine-learning applications. She also explained how societal values are quantified and applied in agent-based multi-agent research.
Nieves then defined theory of mind (ToM), abduction reasoning, and the difference between concepts. Nieves discussed how she built her symbolic-based AI model, TomAbd, that grasped ToM and abductive reasoning. She spoke about the Hanabi game for evaluating her model’s ability.
Nieves explained the theoretical components required to build the TomAbd agent model to play the Hanabi game. She also discussed the metrics to evaluate the agents' performance in learning with ToM and abduction reasoning.
Nieves shared the computation price and the scalability challenges that come with using TomAbd. She, however, also shared the benefits of TomAbd agent models over native deep learning models in certain applications.
Nieves Montes is a PhD student at the Artificial Intelligence Research Institute in Barcelona, working in the Multiagent Systems department under the supervision of Carles Sierra and Nardine Osman. Her research is concerned with socially-oriented AI, through the modeling of values to realize ethically aware software agents, computational models for modeling peers, and the regulation of autonomy through norms. She has published her research on renowned academic journals, such as the Journal of Artificial Intelligence Research and the Journal of Autonomous Agents and Multiagent Systems. Her first contact with this research agenda took place during her master’s thesis at the Autonomous University of Barcelona. Prior to that, she obtained bachelor degrees in Physics and Chemistry from the same university.