Embedded Files
I am a Research Scientist at Meta (FAIR in London). I’m currently focusing on LLM agents and multi-agent reasoning. Previously I’ve worked in Google DeepMind (2018-2024), and before that I've spent some time in the Machine Learning group at Microsoft Research in Cambridge (2009-2017).
My broad research area is artificial intelligence and machine learning, and especially deep learning, reinforcement learning, multiagent systems and game theory, natural language processing and social network analysis.
Below are a few examples of my work. For a full list of publications, please see Google Scholar and DBLP (and patents).
Contact me:
Email: yorambac at gmail.com
Negotiation and honesty in artificial intelligence methods for the board game of Diplomacy
Nature Communications, 2022
Learning to Play No-Press Diplomacy with Best Response Policy Iteration
NeurIPS 2020
Media: Spectrum, VentureBeat, TechRepublic, Gigazine
(Reinforcement learning, multiagent systems)
Cooperative AI: machines must learn to find common ground
Nature (Commentary), 2021
Open Problems in Cooperative AI
(Machine learning, multiagent systems, human-AI collaboration)
Negotiating team formation using deep reinforcement learning
Artificial Intelligence Journal, 2020
(Reinforcement learning, multiagent systems, game theory)
Game-theoretic Vocabulary Selection via the Shapley Value and Banzhaf Index
NAACL 2022
(NLP, Game Theory)
Batch Policy Gradient Methods for Improving Neural Conversation Models
ICLR 2017
(Language models, NLP, deep learning, reinforcement learning)
Inferring Perceived Demographics from User Emotional Tone and User-Environment Emotional Contrast
(NLP, social network analysis)
Studying User Income through Language, Behaviour and Affect in Social Media
PLOS One, 2015
(NLP, social network analysis)
Media: CNBC, Fortune, Atlantic, Scientific American, Telegraph, Daily Mail, City AM, ZDNet, Metro
Neural Payoff Machines: Predicting Fair and Stable Payoff Allocations Among Team Members
NeurIPS 2022
(Deep Learning, Game Theory, Explainable AI)
Nature Medicine, 2023
Media: New Scientist, Medium, Medicalxpress, Gillett, Clayton, Fagen, AdvisoryBoard,
(Deep learning, human-AI collaboration)
A Neural Network Auction For Group Decision Making Over a Continuous Space
IJCAI 2021
(Deep learning, auctions)
The Body is Not a Given: Joint Agent Policy Learning and Morphology Evolution
AAMAS 2019
(Reinforcement learning, multiagent systems)
Designing all-pay auctions using deep learning and multi-agent simulation
Nature Scientific Reports, 2022
(Reinforcement learning, auctions, crowdsourcing)
Biases for Emergent Communication in Multi-agent Reinforcement Learning
NeurIPS 2019
(reinforcement learning, multiagent communication)
Bitcoin Mining Pools: A Cooperative Game Theoretic Analysis
AAMAS 2015
(Game theory, cryptocurrencies)
Speeding up the Xbox recommender system using a euclidean transformation for inner-product spaces
RecSys 2014
(Recommender systems)
Page updated
Google Sites
Report abuse