To achieve general intelligence, agents must learn how to interact with others in a shared environment: this is the challenge of multiagent reinforcement learning (MARL). The simplest form is independent reinforcement learning (InRL), where each agent treats its experience as part of its (non-stationary) environment. In this paper, we first observe that policies learned using InRL can overfit to the other agents' policies during training, failing to sufficiently generalize during execution. We introduce a new metric, joint-policy correlation, to quantify this effect. We describe an algorithm for general MARL, based on approximate best respons
Lanctot, Marc, Zambaldi, Vinicius, Gruslys, Audrunas, Lazaridou, Angeliki, Tuyls, Karl, Perolat, Julien, Silver, David, Graepel, Thore
Research paper by Elguja Abuladze and collaborators, published 2026 in JuSER (Forschungszentrum Jülich). Research area: Seismology and Earthquake Studies.
Elguja Abuladze, I. Bekman, Vesselin Dimitrov, Chimezie Eguzo, André Zambanini, Stefan van Waasen, Qader Dorosti
Research paper by David Stutz and collaborators, published 2026 in Nature. Research area: Law, AI, and Intellectual Property.
David Stutz, Alexander I. Cowen-Rivers, Guillermo Ortiz-Jiménez, Jeremy D. Ratcliff, Vinícius Zambaldi, Lindsay Willmore, Josh Abramson, Harshnira Hitesh Patani, Christina Kouridi, Florian Stimberg, Mel Vecerík, Alex Chu, Sukhdeep Singh, Sumanth Dathathri, Eliseo Papa, Valentin De Bortoli, Arnaud Doucet B, Demis Hassabis, Jue Wang, Sven Gowal, Pushmeet Kohli
Wide use and availability of the machine learning and computer vision techniques allows development of relatively complex monitoring systems in many domains. Besides the traditional industrial domain, new application appears also in biology and agriculture, where we could speak about the detection of infections, parasites and weeds, but also about automated monitoring and early warning systems. This is also connected with the introduction of the easily accessible hardware and development kits such as Arduino, or RaspberryPi family. In this paper, we survey 50 existing papers focusing on the methods of automated beehive monitoring methods usin
Bilik, Simon, Zemcik, Tomas, Kratochvila, Lukas, Ricanek, Dominik, Richter, Milos, Zambanini, Sebastian, Horak, Karel
Matrix games like Prisoner's Dilemma have guided research on social dilemmas for decades. However, they necessarily treat the choice to cooperate or defect as an atomic action. In real-world social dilemmas these choices are temporally extended. Cooperativeness is a property that applies to policies, not elementary actions. We introduce sequential social dilemmas that share the mixed incentive structure of matrix game social dilemmas but also require agents to learn policies that implement their strategic intentions. We analyze the dynamics of policies learned by multiple self-interested independent learning agents, each using its own deep Q-
Leibo, Joel Z., Zambaldi, Vinicius, Lanctot, Marc, Marecki, Janusz, Graepel, Thore
Research paper by Pallavi Zambare and collaborators. arXiv record dated 2025-08-12. Research area: Artificial intelligence.
Pallavi Zambare, Venkata Nikhil Thanikella, Nikhil Padmanabh Kottur, Sree Akhil Akula, Ying Liu
As part of its digitization initiative, the German Central Bank (Deutsche Bundesbank) wants to examine the extent to which natural Language Processing (NLP) can be used to make independent decisions upon the eligibility criteria of securities prospectuses. Every month, the Directorate General Markets at the German Central Bank receives hundreds of scanned prospectuses in PDF format, which must be manually processed to decide upon their eligibility. We found that this tedious and time-consuming process can be (semi-)automated by employing modern NLP model architectures, which learn the linguistic feature representation in text to identify the
Hänig, Christian, Schlösser, Markus, Hamotskyi, Serhii, Zambaku, Gent, Blankenburg, Janek
Research paper by Kiana Aghakasiri and collaborators. arXiv record dated 2025-09-17. Research area: Language technology.
Kiana Aghakasiri, Noopur Zambare, JoAnn Thai, Carrie Ye, Mayur Mehta, J. Ross Mitchell, Mohamed Abdalla
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games. OpenSpiel supports n-player (single- and multi- agent) zero-sum, cooperative and general-sum, one-shot and sequential, strictly turn-taking and simultaneous-move, perfect and imperfect information games, as well as traditional multiagent environments such as (partially- and fully- observable) grid worlds and social dilemmas. OpenSpiel also includes tools to analyze learning dynamics and other common evaluation metrics. This document serves both as an overview of the code base and an introduction to the terminol
Lanctot, Marc, Lockhart, Edward, Lespiau, Jean-Baptiste, Zambaldi, Vinicius, Upadhyay, Satyaki, Pérolat, Julien, Srinivasan, Sriram, Timbers, Finbarr, Tuyls, Karl, Omidshafiei, Shayegan, Hennes, Daniel, Morrill, Dustin, Muller, Paul, Ewalds, Timo, Faulkner, Ryan, Kramár, János, De Vylder, Bart, Saeta, Brennan, Bradbury, James, Ding, David, Borgeaud, Sebastian, Lai, Matthew, Schrittwieser, Julian, Anthony, Thomas, Hughes, Edward, Danihelka, Ivo, Ryan-Davis, Jonah
Artificial intelligence (AI) has undergone a renaissance recently, making major progress in key domains such as vision, language, control, and decision-making. This has been due, in part, to cheap data and cheap compute resources, which have fit the natural strengths of deep learning. However, many defining characteristics of human intelligence, which developed under much different pressures, remain out of reach for current approaches. In particular, generalizing beyond one's experiences--a hallmark of human intelligence from infancy--remains a formidable challenge for modern AI. The following is part position paper, part review, and part uni
Battaglia, Peter W., Hamrick, Jessica B., Bapst, Victor, Sanchez-Gonzalez, Alvaro, Zambaldi, Vinicius, Malinowski, Mateusz, Tacchetti, Andrea, Raposo, David, Santoro, Adam, Faulkner, Ryan, Gulcehre, Caglar, Song, Francis, Ballard, Andrew, Gilmer, Justin, Dahl, George, Vaswani, Ashish, Allen, Kelsey, Nash, Charles, Langston, Victoria, Dyer, Chris, Heess, Nicolas, Wierstra, Daan, Kohli, Pushmeet, Botvinick, Matt, Vinyals, Oriol, Li, Yujia, Pascanu, Razvan
Research paper by Pallavi Zambare and collaborators. arXiv record dated 2025-08-12. Research area: Artificial intelligence.
Pallavi Zambare, Venkata Nikhil Thanikella, Ying Liu
Research paper by Pallavi Zambare and collaborators. arXiv record dated 2025-07-25. Research area: Computer vision.
Pallavi Zambare, Venkata Nikhil Thanikella, Ying Liu
