NICOLO' BRANDIZZI

Dottore di ricerca

ciclo: XXXVI


supervisore: Luca Iocchi
co-supervisore: Roberto Navigli

Titolo della tesi: Conversational Agents in Human-Machine Interaction : Reinforcement Learning and Theory of Mind in Language Modeling

This doctoral thesis addresses the challenges and advancements in the realm of Human-Machine Interaction, specifically focusing on the agency and misalignment of modern Large Language Models. Initially, we examined the potential for artificial agents to manifest agency within an environment inspired by Social Deduction Games, where Multi-Agent System and Reinforcement Learning shape the interactions. Our findings revealed that introducing a communication channel significantly improved agents’ performance, indicative of emergent decision-making abilities. Subsequently, the investigation shifted to the capability of machines to convey information in a manner comprehensible to humans. Through a Referential Game, we identified that agents, while capable of collaboration, struggled with performance when faced with knowledge asymmetry. To address this, we implemented a Multi-Agent Reinforcement Learning approach, aligning with contemporary solutions in the literature and show how it ultimately culminated in the issue of misalignment. In response, our final approach integrated elements from psychology and linguistics to propose a solution to both issues of agency and misalignment. We showed how our method improved communication accuracies solving the agency issue and mitigating the misalignment problem. Moreover, we highlight the environmental and interpretability advantages of our solution. We conclude by stressing the importance of interdisciplinary approaches to refine and understand the capabilities of artificial agents in communication-centric tasks.

Produzione scientifica

11573/1683239 - 2023 - Unsupervised Pose Estimation by Means of an Innovative Vision Transformer
Brandizzi, N.; Fanti, A.; Gallotta, R.; Russo, S.; Iocchi, L.; Nardi, D.; Napoli, C. - 04b Atto di convegno in volume
congresso: International Conference on Artificial Intelligence and Soft Computing (Zakopane; Poland)
libro: Artificial Intelligence and Soft Computing 21st International Conference, ICAISC 2022, Zakopane, Poland, June 19–23, 2022, Proceedings, Part II - (978-3-031-23479-8; 978-3-031-23480-4)

11573/1664529 - 2022 - Addressing Vehicle Sharing through Behavioral Analysis: A Solution to User Clustering Using Recency-Frequency-Monetary and Vehicle Relocation Based on Neighborhood Splits
Brandizzi, N.; Russo, S.; Galati, G.; Napoli, C. - 01a Articolo in rivista
rivista: INFORMATION (Basel: Molecular Diversity Preservation International) pp. - - issn: 2078-2489 - wos: WOS:000881181500001 (2) - scopus: 2-s2.0-85141781221 (20)

11573/1664524 - 2022 - Human Attention Assessment Using A Machine Learning Approach with GAN-based Data Augmentation Technique Trained Using a Custom Dataset
Pepe, S.; Tedeschi, S.; Brandizzi, N.; Russo, S.; Iocchi, L.; Napoli, C. - 01a Articolo in rivista
rivista: OBM NEUROBIOLOGY (Beachwood OH: Open Biomedical Publishing Corporation) pp. - - issn: 2573-4407 - wos: (0) - scopus: 2-s2.0-85144152564 (20)

11573/1625561 - 2021 - A Customized Approach to Anomalies Detection by using Autoencoders
Aureli, R.; Brandizzi, N.; De Magistris, G.; Brociek, R. - 04b Atto di convegno in volume
congresso: 2021 Scholar's Yearly Symposium of Technology, Engineering and Mathematics, SYSTEM 2021 (Catania; Italia)
libro: SYSTEM 2021 Scholar’s Yearly Symposium of Technology, Engineering and Mathematics 2021 - ()

11573/1627179 - 2021 - Automatic RGB Inference Based on Facial Emotion Recognition
Brandizzi, N.; Bianco, V.; Castro, G.; Russo, S.; Wajda, A. - 04b Atto di convegno in volume
congresso: 2021 Scholar's Yearly Symposium of Technology, Engineering and Mathematics, SYSTEM 2021 (Catania, Italy)
libro: Proceedings of the Scholar’s Yearly Symposium of Technology, Engineering and Mathematics (SYSTEM 2021) - ()

11573/1623692 - 2021 - FEFFuL: A Few-Examples Fitness Function Learner
Brandizzi, N.; Fanti, A.; Gallotta, R.; Napoli, C. - 04b Atto di convegno in volume
congresso: 2021 Scholar's Yearly Symposium of Technology, Engineering and Mathematics, SYSTEM 2021 (Catania; Italia)
libro: SYSTEM 2021 Scholar’s Yearly Symposium of Technology, Engineering and Mathematics 2021 - ()

11573/1618078 - 2021 - RLupus: cooperation through emergent communication in the werewolf social deduction game
Brandizzi, N.; Grossi, D.; Iocchi, L. - 01a Articolo in rivista
rivista: INTELLIGENZA ARTIFICIALE (Associazione Italiana per l'Intelligenza Artificiale) pp. 55-70 - issn: 1724-8035 - wos: WOS:000752870100001 (1) - scopus: 2-s2.0-85124674470 (1)

© Università degli Studi di Roma "La Sapienza" - Piazzale Aldo Moro 5, 00185 Roma