CompetEvo: Towards Morphological Evolution from Competition

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huang, Kangyao, Guo, Di, Zhang, Xinyu, Ji, Xiangyang, Liu, Huaping
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918208425951232
author Huang, Kangyao
Guo, Di
Zhang, Xinyu
Ji, Xiangyang
Liu, Huaping
author_facet Huang, Kangyao
Guo, Di
Zhang, Xinyu
Ji, Xiangyang
Liu, Huaping
contents Training an agent to adapt to specific tasks through co-optimization of morphology and control has widely attracted attention. However, whether there exists an optimal configuration and tactics for agents in a multiagent competition scenario is still an issue that is challenging to definitively conclude. In this context, we propose competitive evolution (CompetEvo), which co-evolves agents' designs and tactics in confrontation. We build arenas consisting of three animals and their evolved derivatives, placing agents with different morphologies in direct competition with each other. The results reveal that our method enables agents to evolve a more suitable design and strategy for fighting compared to fixed-morph agents, allowing them to obtain advantages in combat scenarios. Moreover, we demonstrate the amazing and impressive behaviors that emerge when confrontations are conducted under asymmetrical morphs.
format Preprint
id arxiv_https___arxiv_org_abs_2405_18300
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CompetEvo: Towards Morphological Evolution from Competition
Huang, Kangyao
Guo, Di
Zhang, Xinyu
Ji, Xiangyang
Liu, Huaping
Artificial Intelligence
Training an agent to adapt to specific tasks through co-optimization of morphology and control has widely attracted attention. However, whether there exists an optimal configuration and tactics for agents in a multiagent competition scenario is still an issue that is challenging to definitively conclude. In this context, we propose competitive evolution (CompetEvo), which co-evolves agents' designs and tactics in confrontation. We build arenas consisting of three animals and their evolved derivatives, placing agents with different morphologies in direct competition with each other. The results reveal that our method enables agents to evolve a more suitable design and strategy for fighting compared to fixed-morph agents, allowing them to obtain advantages in combat scenarios. Moreover, we demonstrate the amazing and impressive behaviors that emerge when confrontations are conducted under asymmetrical morphs.
title CompetEvo: Towards Morphological Evolution from Competition
topic Artificial Intelligence
url https://arxiv.org/abs/2405.18300