Network-based modeling of complex systems and data using the language of graphs has become an essential topic across a range of different disciplines. Arguably, this graph-based …
The cornerstone underpinning deep learning is the guarantee that gradient descent on an objective converges to local minima. Unfortunately, this guarantee fails in settings, such as …
Zero-sum games such as chess and poker are, abstractly, functions that evaluate pairs of agents, for example labeling them 'winner'and 'loser'. If the game is approximately transitive …
This is an elementary introduction to the Hodge Laplacian on a graph, a higher-order generalization of the graph Laplacian. We will discuss basic properties including …
Most existing results about last-iterate convergence of learning dynamics are limited to two- player zero-sum games, and only apply under rigid assumptions about what dynamics the …
We introduce α-Rank, a principled evolutionary dynamics methodology, for the evaluation and ranking of agents in large-scale multi-agent interactions, grounded in a novel dynamical …
Promoting behavioural diversity is critical for solving games with non-transitive dynamics where strategic cycles exist, and there is no consistent winner (eg, Rock-Paper-Scissors) …
J Yao, W Liu, H Fu, Y Yang… - Advances in Neural …, 2024 - proceedings.neurips.cc
Abstract Policy-Space Response Oracles (PSRO) is an influential algorithm framework for approximating a Nash Equilibrium (NE) in multi-agent non-transitive games. Many previous …
Progress in machine learning is measured by careful evaluation on problems of outstanding common interest. However, the proliferation of benchmark suites and environments …