[PDF][PDF] Improved algorithms for learning equilibria in simulation-based games
E Areyan Viqueira, C Cousins… - Proceedings of the 19th …, 2020 - aamas.csc.liv.ac.uk
Game theory is the de facto standard conceptual framework used to analyze the strategic
interactions among rational agents in multiagent systems. At the heart of this framework is …
interactions among rational agents in multiagent systems. At the heart of this framework is …
Sharp uniform convergence bounds through empirical centralization
C Cousins, M Riondato - Advances in Neural Information …, 2020 - proceedings.neurips.cc
We introduce the use of empirical centralization to derive novel practical, probabilistic,
sample-dependent bounds to the Supremum Deviation (SD) of empirical means of functions …
sample-dependent bounds to the Supremum Deviation (SD) of empirical means of functions …
Learning probably approximately correct maximin strategies in simulation-based games with infinite strategy spaces
We tackle the problem of learning equilibria in simulation-based games. In such games, the
players' utility functions cannot be described analytically, as they are given through a black …
players' utility functions cannot be described analytically, as they are given through a black …
Empirical mechanism design: Designing mechanisms from data
EA Viqueira, C Cousins… - Uncertainty in …, 2020 - proceedings.mlr.press
We introduce a methodology for the design of parametric mechanisms, which are multiagent
systems inhabited by strategic agents, with knobs that can be adjusted to achieve specific …
systems inhabited by strategic agents, with knobs that can be adjusted to achieve specific …
Learning utilities and equilibria in non-truthful auctions
In non-truthful auctions, agents' utility for a strategy depends on the strategies of the
opponents and also the prior distribution over their private types; the set of Bayes Nash …
opponents and also the prior distribution over their private types; the set of Bayes Nash …
[PDF][PDF] Learning Properties in Simulation-Based Games
C Cousins, B Mishra, E Areyan Viqueira… - Proceedings of the …, 2023 - southampton.ac.uk
In recent years, empirical game-theoretic analysis (EGTA) has emerged as a powerful tool
by which to analyze multiagent systems [2, 22, 23, 28], particularly when only a simulator of …
by which to analyze multiagent systems [2, 22, 23, 28], particularly when only a simulator of …
Computational and Data Requirements for Learning Generic Properties of Simulation-Based Games
C Cousins, B Mishra, EA Viqueira… - arXiv preprint arXiv …, 2022 - arxiv.org
Empirical game-theoretic analysis (EGTA) is primarily focused on learning the equilibria of
simulation-based games. Recent approaches have tackled this problem by learning a …
simulation-based games. Recent approaches have tackled this problem by learning a …
An active learning method for solving competitive multi-agent decision-making and control problems
F Fabiani, A Bemporad - arXiv preprint arXiv:2212.12561, 2022 - arxiv.org
We propose a scheme based on active learning to reconstruct private strategies executed by
a population of interacting agents and predict an exact outcome of the underlying multi …
a population of interacting agents and predict an exact outcome of the underlying multi …
Learning competitive equilibria in noisy combinatorial markets
We present a methodology to robustly estimate the competitive equilibria (CE) of
combinatorial markets under the assumption that buyers do not know their precise …
combinatorial markets under the assumption that buyers do not know their precise …
Regret Pruning for Learning Equilibria in Simulation-Based Games
B Mishra, C Cousins, A Greenwald - arXiv preprint arXiv:2211.16670, 2022 - arxiv.org
In recent years, empirical game-theoretic analysis (EGTA) has emerged as a powerful tool
for analyzing games in which an exact specification of the utilities is unavailable. Instead …
for analyzing games in which an exact specification of the utilities is unavailable. Instead …