Tournament-informed task selection in adversarial QD produces higher quality and diversity in coevolved solutions across Pong, cat-and-mouse, and pursuers-evaders games.
Multi-agent diagnostics for robustness via illuminated diversity
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.NE 2verdicts
UNVERDICTED 2representative citing papers
GAME is a new adversarial coevolutionary QD algorithm using generational alternation and vision embeddings that outperforms one-sided baselines across battle, wrestling, and deck-building tasks while revealing arms-race dynamics and the role of neutral mutations.
citing papers explorer
-
Tournament Informed Adversarial Quality Diversity
Tournament-informed task selection in adversarial QD produces higher quality and diversity in coevolved solutions across Pong, cat-and-mouse, and pursuers-evaders games.
-
Adversarial Coevolutionary Illumination with Generational Adversarial MAP-Elites
GAME is a new adversarial coevolutionary QD algorithm using generational alternation and vision embeddings that outperforms one-sided baselines across battle, wrestling, and deck-building tasks while revealing arms-race dynamics and the role of neutral mutations.