10 citations · 15 across the 18 of their papers we have counts for
19 papers
Multiplicative Optimism for Constant Regret in Games
Ashkan Soleymani, Georgios Piliouras
We introduce Multiplicatively Optimistic Regret Matching (MORM), an uncoupled learning rule for finite general-sum games. Under simultaneous full-information self-play, every playe…
Paradoxes of Game Theoretic Equilibria and Price of Anarchy
Georgios Piliouras, Ian Gemp, Siqi Liu +1
For decades, static solution concepts (Nash, Correlated, and Coarse Correlated Equilibria) and the Price of Anarchy (PoA) have formed the bedrock of algorithmic game theory, with n…
Debate is efficient with your time
Jonah Brown-Cohen, Geoffrey Irving, Simon C. Marshall +3
AI safety via debate uses two competing models to help a human judge verify complex computational tasks. Previous work has established what problems debate can solve in principle,…
Avoiding Obfuscation with Prover-Estimator Debate
Jonah Brown-Cohen, Geoffrey Irving, Georgios Piliouras +3
Training powerful AI systems to exhibit desired behaviors hinges on the ability to provide accurate human supervision on increasingly complex tasks. A promising approach to this pr…
Cautious Optimism: A Meta-Algorithm for Near-Constant Regret in General Games
Ashkan Soleymani, Georgios Piliouras, Gabriele Farina
We introduce Cautious Optimism, a framework for substantially faster regularized learning in general games. Cautious Optimism, as a variant of Optimism, adaptively controls the lea…
Plasticity as the Mirror of Empowerment
David Abel, Michael Bowling, André Barreto +13
Agents are minimally entities that are influenced by their past observations and act to influence future observations. This latter capacity is captured by empowerment, which has se…
Faster Rates for No-Regret Learning in General Games via Cautious Optimism
Ashkan Soleymani, Georgios Piliouras, Gabriele Farina
We establish the first uncoupled learning algorithm that attains per-player regret in multi-player general-sum games, where is the number of players, …
Multi-Agent Risks from Advanced AI
Lewis Hammond, Alan Chan, Jesse Clifton +41
The rapid development of advanced AI agents and the imminent deployment of many instances of these agents will give rise to multi-agent systems of unprecedented complexity. These s…
Deviation Ratings: A General, Clone-Invariant Rating Method
Luke Marris, Siqi Liu, Ian Gemp +2
Many real-world multi-agent or multi-task evaluation scenarios can be naturally modelled as normal-form games due to inherent strategic (adversarial, cooperative, and mixed motive)…
Agency Is Frame-Dependent
David Abel, André Barreto, Michael Bowling +13
Agency is a system's capacity to steer outcomes toward a goal, and is a central topic of study across biology, philosophy, cognitive science, and artificial intelligence. Determini…
Re-evaluating Open-ended Evaluation of Large Language Models
Siqi Liu, Ian Gemp, Luke Marris +3
Evaluation has traditionally focused on ranking candidates for a specific skill. Modern generalist models, such as Large Language Models (LLMs), decidedly outpace this paradigm. Op…
A theory of appropriateness with applications to generative artificial intelligence
Joel Z. Leibo, Alexander Sasha Vezhnevets, Manfred Diaz +11
What is appropriateness? Humans navigate a multi-scale mosaic of interlocking notions of what is appropriate for different situations. We act one way with our friends, another with…
Convex Markov Games: A New Frontier for Multi-Agent Reinforcement Learning
Ian Gemp, Andreas Haupt, Luke Marris +2
Behavioral diversity, expert imitation, fairness, safety goals and others give rise to preferences in sequential decision making domains that do not decompose additively across tim…
Visualizing 2x2 Normal-Form Games: twoxtwogame LaTeX Package
Luke Marris, Ian Gemp, Siqi Liu +2
Normal-form games with two players, each with two strategies, are the most studied class of games. These so-called 2x2 games are used to model a variety of strategic interactions.…
NfgTransformer: Equivariant Representation Learning for Normal-form Games
Siqi Liu, Luke Marris, Georgios Piliouras +2
Normal-form games (NFGs) are the fundamental model of strategic interaction. We study their representation using neural networks. We describe the inherent equivariance of NFGs -- a…
Approximating the Core via Iterative Coalition Sampling
Ian Gemp, Marc Lanctot, Luke Marris +11
The core is a central solution concept in cooperative game theory, defined as the set of feasible allocations or payments such that no subset of agents has incentive to break away…
Steering Language Models with Game-Theoretic Solvers
Ian Gemp, Roma Patel, Yoram Bachrach +6
Mathematical models of interactions among rational agents have long been studied in game theory. However these interactions are often over a small set of discrete game actions whic…
Neural Population Learning beyond Symmetric Zero-sum Games
Siqi Liu, Luke Marris, Marc Lanctot +3
We study computationally efficient methods for finding equilibria in n-player general-sum games, specifically ones that afford complex visuomotor skills. We show how existing metho…
Scalable AI Safety via Doubly-Efficient Debate
Jonah Brown-Cohen, Geoffrey Irving, Georgios Piliouras
The emergence of pre-trained AI systems with powerful capabilities across a diverse and ever-increasing set of complex domains has raised a critical challenge for AI safety as task…