analiza aiqbench
This research advances autonomous control by utilizing "The Core," a competitive co-evolution algorithm that generates agents without traditional fitness functions. By niching these agents to specific environmental subsets, the study demonstrates improved success rates compared to systems evolved for entire environments or disparate sub-environments. This work contributes directly to the field of machine learning by exploring novel evolutionary strategies for agent autonomy.
Niching Agents in The Core
arXiv:2609.12398v1 Announce Type: new Abstract: The Core is a unique competitive co-evolution algorithm that allows agents to evolve autonomous control without utilizing a traditional fitness function. The agents evolve via local interactions through tournament selection, crossover, and mutation, producing offspring by evolving better controllers. Previous works have shown The Core's ability to evolve agents capable of combat and navigation in the Xpilot video game. This research expands upon that premise by niching agents to specific subsets of the original environment The Core was tested in. Our results demonstrate the niched agents capacity for success over agents niched to the entire system and agents niched to different sub-environments.
Abstract:The Core is a unique competitive co-evolution algorithm that allows agents to evolve autonomous control without utilizing a traditional fitness function. The agents evolve via local interactions through tournament selection, crossover, and mutation, producing offspring by evolving better controllers. Previous works have shown The Core's ability to evolve agents capable of combat and navigation in the Xpilot video game. This research expands upon that premise by niching agents to specific subsets of the original environment The Core was tested in. Our results demonstrate the niched agents capacity for success over agents niched to the entire system and agents niched to different sub-environments.
Artificial Intelligence (cs.AI)
arXiv:2609.12398 [cs.AI]
(or arXiv:2609.12398v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.12398 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
https://doi.org/10.1007/978-3-032-15635-8_16 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 206 cuvinte
Subiecte conexe

[AINews] Opus 5.5 is good at explainer videos
Latent Space · 29 sept. 2026

[AINews] The Future of Latent Space
Latent Space · 25 sept. 2026
State of the Field: AI for Epistemics and Coordination
LessWrong · 2 oct. 2026
Open models recap: more on Kimi K3, Qwen 3.8, Xi's WAIC speech, distillation, the open-closed gap, and what's next
Interconnects · 22 iul. 2026