114 citations · 813 across the 92 of their papers we have counts for
10 papers · 1 filter
Evolutionary Game Theory Squared: Evolving Agents in Endogenously Evolving Zero-Sum Games
Stratis Skoulakis, Tanner Fiez, Ryann Sim +2
The predominant paradigm in evolutionary game theory and more generally online learning in games is based on a clear distinction between a population of dynamic agents that interac…
Exploration-Exploitation in Multi-Agent Learning: Catastrophe Theory Meets Game Theory
Stefanos Leonardos, Georgios Piliouras
Exploration-exploitation is a powerful and practical tool in multi-agent learning (MAL), however, its effects are far from understood. To make progress in this direction, we study…
Exploring the Predictability of Cryptocurrencies via Bayesian Hidden Markov Models
Constandina Koki, Stefanos Leonardos, Georgios Piliouras
In this paper, we consider a variety of multi-state Hidden Markov models for predicting and explaining the Bitcoin, Ether and Ripple returns in the presence of state (regime) dynam…
Efficient Online Learning of Optimal Rankings: Dimensionality Reduction via Gradient Descent
Dimitris Fotakis, Thanasis Lianeas, Georgios Piliouras +1
We consider a natural model of online preference aggregation, where sets of preferred items along with a demand for items in each , appear online…
No-regret learning and mixed Nash equilibria: They do not mix
Lampros Flokas, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Thanasis Lianeas +2
Understanding the behavior of no-regret dynamics in general -player games is a fundamental question in online learning and game theory. A folk result in the field states that, i…
Data-Driven Models of Selfish Routing: Why Price of Anarchy Does Depend on Network Topology
Francisco Benita, Vittorio Bilò, Barnabé Monnot +2
We investigate traffic routing both from the perspective of theory as well as real world data. First, we introduce a new type of games: -free flow games. Here, commuters only co…
Catastrophe by Design in Population Games: Destabilizing Wasteful Locked-in Technologies
Stefanos Leonardos, Iosif Sakos, Costas Courcoubetis +1
In multi-agent environments in which coordination is desirable, the history of play often causes lock-in at sub-optimal outcomes. Notoriously, technologies with a significant envir…
Chaos, Extremism and Optimism: Volume Analysis of Learning in Games
Yun Kuen Cheung, Georgios Piliouras
We present volume analyses of Multiplicative Weights Updates (MWU) and Optimistic Multiplicative Weights Updates (OMWU) in zero-sum as well as coordination games. Such analyses pro…
From Poincaré Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization
Julien Perolat, Remi Munos, Jean-Baptiste Lespiau +10
In this paper we investigate the Follow the Regularized Leader dynamics in sequential imperfect information games (IIG). We generalize existing results of Poincaré recurrence from…
Smooth markets: A basic mechanism for organizing gradient-based learners
David Balduzzi, Wojciech M Czarnecki, Thomas W Anthony +5
With the success of modern machine learning, it is becoming increasingly important to understand and control how learning algorithms interact. Unfortunately, negative results from…