Zobrazeno 1 - 10
of 85
pro vyhledávání: '"Hoover, Amy"'
We consider a setting where a population of artificial learners is given, and the objective is to optimize aggregate measures of performance, under constraints on training resources. The problem is motivated by the study of peer learning in human edu
Externí odkaz:
http://arxiv.org/abs/2312.00660
Autor:
Meyerson, Elliot, Nelson, Mark J., Bradley, Herbie, Gaier, Adam, Moradi, Arash, Hoover, Amy K., Lehman, Joel
This paper pursues the insight that language models naturally enable an intelligent variation operator similar in spirit to evolutionary crossover. In particular, language models of sufficient scale demonstrate in-context learning, i.e. they can lear
Externí odkaz:
http://arxiv.org/abs/2302.12170
This paper proposes a framework called Watts for implementing, comparing, and recombining open-ended learning (OEL) algorithms. Motivated by modularity and algorithmic flexibility, Watts atomizes the components of OEL systems to promote the study of
Externí odkaz:
http://arxiv.org/abs/2204.13250
PINSKY is a system for open-ended learning through neuroevolution in game-based domains. It builds on the Paired Open-Ended Trailblazer (POET) system, which originally explored learning and environment generation for bipedal walkers, and adapts it to
Externí odkaz:
http://arxiv.org/abs/2203.10941
We study the problem of efficiently generating high-quality and diverse content in games. Previous work on automated deckbuilding in Hearthstone shows that the quality diversity algorithm MAP-Elites can generate a collection of high-performing decks
Externí odkaz:
http://arxiv.org/abs/2112.03534
Autor:
Zhang, Hejia, Fontaine, Matthew C., Hoover, Amy K., Togelius, Julian, Dilkina, Bistra, Nikolaidis, Stefanos
Recent advancements in procedural content generation via machine learning enable the generation of video-game levels that are aesthetically similar to human-authored examples. However, the generated levels are often unplayable without additional edit
Externí odkaz:
http://arxiv.org/abs/2010.06627
Autor:
Fontaine, Matthew C., Liu, Ruilin, Khalifa, Ahmed, Modi, Jignesh, Togelius, Julian, Hoover, Amy K., Nikolaidis, Stefanos
Generative adversarial networks (GANs) are quickly becoming a ubiquitous approach to procedurally generating video game levels. While GAN generated levels are stylistically similar to human-authored examples, human designers often want to explore the
Externí odkaz:
http://arxiv.org/abs/2007.05674
We focus on the challenge of finding a diverse collection of quality solutions on complex continuous domains. While quality diver-sity (QD) algorithms like Novelty Search with Local Competition (NSLC) and MAP-Elites are designed to generate a diverse
Externí odkaz:
http://arxiv.org/abs/1912.02400
Games have benchmarked AI methods since the inception of the field, with classic board games such as Chess and Go recently leaving room for video games with related yet different sets of challenges. The set of AI problems associated with video games
Externí odkaz:
http://arxiv.org/abs/1907.06562