I am a Staff Research Scientist at Google DeepMind. My research focuses on Multi-agent methods for Large Language Models and Mechanism Design.
I obtained my PhD from MIT where I was part of the Computer Science and Artificial Intelligence Laboratory. My thesis advisor was Tomaso Poggio.
Before Graduate School I was part of the Equipment Controls and Electronic section in the Engineering Department at CERN.
Contacts and Links
Scaffolding cooperation in human groups with deep reinforcement learning, McKee K, Tacchetti A, Bakker M, Balaguer J, Campbell-Gillingham L, Everett R, Botvinick M, 2022
The Good Shepherd: An Oracle Agent for Mechanism Design. Balaguer J, Koster R, Summerfield C, Tacchetti A; 2022
HCMD-zero: Learning Value Aligned Mechanisms from Data. Balaguer J, Koster R, Weinstein A, Campbell-Gillingham L, Summerfield C, Botvinick M, Tacchetti A; 2022
Human-centered mechanism design with Democratic AI. Koster R, Balaguer J, Tacchetti A, Weinstein A, Zhu T, Hauser O, Williams D, Campbell-Gillingham L, Thacher P, Botvinick M, Summerfield C' 2022
Sample-based Approximation of Nash in Large Many-Player Games via Gradient Descent. Gemp I, Savani R, Lanctot M, Bachrach Y, Anthony T, Everett R, Tacchetti A, Eccles T, Kramár J; 2021
D3C: Reducing the Price of Anarchy in Multi-Agent Learning. Gemp I, McKee K, Everett R, Duéñez-Guzmán E, Bachrach Y, Balduzzi D, Tacchetti A; 2021
Learning to Play No-Press Diplomacy with Best Response Policy Iteration. Anthony T*, Eccles T*, Tacchetti A, Kramár J, Gemp I, Hudson TC, Porcel N, Lanctot M, Pérolat J, Everett J, Singh S, Graepel T, Bachrach Y; 2020
A Neural Architecture for Designing Truthful and Efficient Auctions. Tacchetti A, Strouse DJ, Garnelo M, Graepel T, Bachrach Y; 2019
Relational Forward Models for Multi-Agent Learning. Tacchetti A*, Song H F*, Mediano P A M*, Zambaldi V, Rabinowitz N C, Graepel T, Botvinick M, Battaglia P; 2018
Visual Interaction Networks. Watters N, Tacchetti A, Weber T, Pascanu R, Battaglia P, Zoran D; 2017
Invariant recognition drives neural representations of action sequences. Tacchetti A*, Isik L* Poggio T; 2017
Discriminiate-and-rectify Encoders: Learning from Image Transfromation Sets. Tacchetti A*, Voinea S*, Evangelopoulos G; 2017
Fast, invariant representations for human actions in the visual system. Isik L*, Tacchetti A*, Poggio T; 2016
Regularization by Early Stopping for Online Learning Algorithms. Rosasco L, Tacchetti A, Villa S; 2014 (updated version by Rosasco L, and Villa S. 2015)
Does invariant recognition predict tuning of neurons in sensory cortex? Poggio T, Mutch J, Anselmi F, Tacchetti A, Rosasco R, Leibo J; 2013
Unsupervised learning of invariant representations in hierarchical architectures. Anselmi F, Joel L, Rosasco L, Mutch J, Tacchetti A, Poggio T; 2013
Turbocharging Solution Concepts: Solving NEs, CEs and CCEs with Neural Equilibrium Solvers, Marris L, Gemp I, Anthony T, Tacchetti A, Liu S, Tuyls K, Neural Information Processing Systems (NeurIPS) 2022
Teamwork Reinforcement Learning with Concave Utilities. Yu Z, Zhang J, Wen Z, Tacchetti A, Wang M, Gemp I, ICLR 2022 Workshop on Gamification and Multiagent Solutions. 2022
Learning to Play No-Press Diplomacy with Best Response Policy Iteration. Anthony T, Eccles T, Tacchetti A, Kramár J, Gemp I, Hudson T, Porcel N, Lanctot M, Perolat J, Everett R, Singh S, Graepel T, Bachrach Y; Neural Information Processing Systems (NeurIPS) 2020 (Spotlight talk)
Should I tear down this wall? Optimizing social metrics by evaluating novel actions. Kramár J, Rabinowitz N, Eccles T, Tacchetti A; International Workshop on Coordination, Organizations, Institutions, Norms and Ethics for Governance of Multi-Agent Systems (COINE) 2020.
Relational Forward Models for Multi-agent learning. Tacchetti A, Song HF, Mediano, PAM, Zambaldi V, Kramár, Rabinowitz NC, Graepel T, Botvinick M, Battaglia P; International Conference on Learning Representations (ICLR) 2019.
Trading robust representations for sample complexity through self-supervised visual experience. Tacchetti A, Voinea S, Evangelopoulos G; Neural Information Processing Systems (NeurIPS) 2018
Visual Interaction Networks: Learning a Physics Simulator from Video. Watters N, Tacchetti A, Weber T, Pascanu R, Battaglia P, Zoran D; Neural Information Processing Systems (NeurIPS) 2017
Invariant recognition drives neural representations of action sequences. Isik L*, Tacchetti A*, Poggio T; Cognitive Computational Neuroscience; 2017
Representation Learning from Orbit Sets for One-Shot Classification. Tacchetti A*, Voinea S*, Evangelopoulos G, Poggio T; 2017 AAAI Spring Symposium Series; 2017
Invariant representations for action recognition in the visual system. Tacchetti A*, Isik L*, Poggio, T. Journal of Vision (Oral Presentation at VSS); 2015
Invariant representations for action recognition in the visual system. Isik L*, Tacchetti A*, Poggio, T. Computational and Systems Neuroscience (COSYNE); 2015
Invariant representations of action recognition. Isik L*, Tacchetti A*, Poggio T; Society for Neuroscience 2014.
Readout of dynamic action sequences using MEG decoding. Isik L, Tacchetti A, Poggio T; Biomagnetism, 2014.
Implementation and tuning of the Extended Kalman Filter for a sensorless drive working with arbitrary stepper motors and cable lengths. Butcher M, Masi A, Martino M, Tacchetti A; International Conference on Electrical Machines (ICEM). 2012.
GURLS: a Toolbox for Large Scale Multiclass Learning. Tacchetti A, Mallapragada P, Santoro M, Rosasco L. NeurIPS Workshop on Parallel and Large-Scale Machine Learning; 2011
Negotiation and honesty in artificial intelligence methods for the board game of Diplomacy, Kramár J, Eccles T, Gemp I, Tacchetti A, McKee K, Malinowski M, Graepel T, Bachrach Y, Nature Communications 2022
Designing all-pay auctions using deep learning and multi-agent simulation, Gemp I, Anthony T, Kramar J, Eccles T, Tacchetti A, Bachrach Y, Nature Scientific Reports 2022
Human-centred mechanism design with Democratic AI, Koster R, Balaguer J, Tacchetti A, Weinstein A, Zhu T, Hauser O, Williams D, Campbell-Gillingham L, Thacker P, Botvinick M, Summerfield C. Nature Human Behavior 2022
Evaluating Strategic Structures in Multi-Agent Inverse Reinforcement Learning. Fu J, Tacchetti A, Perolat J, Bachrach Y; JAIR, 2021
Invariant Recognition Shapes Neural Representations of Visual Input. Tacchetti A, Isik L, Poggio T. Annual Reviews of Vision Science; 2018
Invariant recognition drives neural representations of action sequences. Tacchetti A*, Isik L*, Poggio T. PLOS Computational Biology; 2017
A fast, invariant representation for human action in the visual system. Isik L*, Tacchetti A*, Poggio T; Journal of Neurophysiology, 2017 (selected for APSselect, a collection from the APS that showcases some of the best recently published articles in physiological research).
Unsupervised learning or invariant representations. Anselmi F, Leibo J, Rosasco L, Mutch J, Tacchetti A, Poggio T; Theoretical Computer Science, 2015.
GURLS: A Least Squares Library for Supervised Learining. Tacchetti A, Mallapragada P, Santoro M, Rosasco L; Journal of Machine Learning Research 14, 3201-3205, 2013.
Invariant Recognition Predicts Tuning of Neurons in Sensory Cortex. Mutch J, Anselmi F, Tacchetti A, Rosasco L, Leibo J, Poggio T; Computational and Cognitive Neuroscience of Vision, 2016.
Learning Invariant Representations of Actions and Faces. Tacchetti A. PhD Thesis, MIT, Department of Electrical Engineering and Computer Science, 2018.
Google’s ‘Democratic AI’ Is Better at Redistributing Wealth Than America. Janus Rose, VICE 2022
DeepMind sets AI loose on Diplomacy board game, and collaboration is key. R. Dallon Adams. TechRepublic. 2020
DeepMind hopes to teach AI to cooperate by playing Diplomacy. Kyle Wiggers. Venture Beat. 2020
Want to understand the mind of another? Get relational!. Jack Clark. Import AI. 2018
Forget AlphaGo — DeepMind Has a More Interesting Step Toward General AI. Will Knight, MIT Technology Review. 2017