Using Skill Rating as Fitness on the Evolution of GANs

Costa, Victor; Lourenço, Nuno; Correia, João; Machado, Penousal

doi:10.1007/978-3-030-43722-0_36

Cited by 2 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Evolutionary game theory methods for training generative adversarial networks commonly exhibit timeevolving dynamic behavior and there is a pair of predominant doubly evolutionary process models (Costa et al, 2020;Garciarena et al, 2018;Costa et al, 2019a;Miikkulainen et al, 2019). In the first formulation, describe training the generator network, with parameters y, via a gradient-based algorithm composed of variation, evaluation, and selection.…”

Section: Doubly Evolutionary Behavior In Ai and MLmentioning

confidence: 99%

“…This provides further evidence for the efficacy of recurrence as a solution concept that is relevant to machine learning applications such as generative adversarial networks. A final line of work explores evolutionary algorithms as a training method for generative adversarial networks (Costa et al, 2020;Karras et al, 2018;Costa et al, 2019a,b;Garciarena et al, 2018;Al-Dujaili et al, 2018;Toutouh et al, 2019).…”

Section: A Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Evolutionary Game Theory Squared: Evolving Agents in Endogenously Evolving Zero-Sum Games

Skoulakis¹,

Fiez²,

Sim³

et al. 2020

Preprint

View full text Add to dashboard Cite

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 interact given a fixed, static game. In this paper, we move away from the artificial divide between dynamic agents and static games, to introduce and analyze a large class of competitive settings where both the agents and the games they play evolve strategically over time. We focus on arguably the most archetypal game-theoretic setting-zero-sum games (as well as network generalizations)-and the most studied evolutionary learning dynamic-replicator, the continuous-time analogue of multiplicative weights. Populations of agents compete against each other in a zero-sum competition that itself evolves adversarially to the current population mixture. Remarkably, despite the chaotic coevolution of agents and games, we prove that the system exhibits a number of regularities. First, the system has conservation laws of an informationtheoretic flavor that couple the behavior of all agents and games. Secondly, the system is Poincaré recurrent, with effectively all possible initializations of agents and games lying on recurrent orbits that come arbitrarily close to their initial conditions infinitely often. Thirdly, the time-average agent behavior and utility converge to the Nash equilibrium values of the time-average game. Finally, we provide a polynomial time algorithm to efficiently predict this time-average behavior for any such coevolving network game.

show abstract

Section: Doubly Evolutionary Behavior In Ai and MLmentioning

confidence: 99%