Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2406.09654 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909223646920704 |
|---|---|
| author | Barbieux, Aidan Canaan, Rodrigo |
| author_facet | Barbieux, Aidan Canaan, Rodrigo |
| contents | This paper presents Coralai, a framework for exploring diverse ecosystems of Neural Cellular Automata (NCA). Organisms in Coralai utilize modular, GPU-accelerated Taichi kernels to interact, enact environmental changes, and evolve through local survival, merging, and mutation operations implemented with HyperNEAT and PyTorch. We provide an exploratory experiment implementing physics inspired by slime mold behavior showcasing the emergence of competition between sessile and mobile organisms, cycles of resource depletion and recovery, and symbiosis between diverse organisms. We conclude by outlining future work to discover simulation parameters through measures of multi-scale complexity and diversity. Code for Coralai is available at https://github.com/aidanbx/coralai , video demos are available at https://www.youtube.com/watch?v=NL8IZQY02-8 . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_09654 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Coralai: Intrinsic Evolution of Embodied Neural Cellular Automata Ecosystems Barbieux, Aidan Canaan, Rodrigo Neural and Evolutionary Computing Machine Learning Multiagent Systems This paper presents Coralai, a framework for exploring diverse ecosystems of Neural Cellular Automata (NCA). Organisms in Coralai utilize modular, GPU-accelerated Taichi kernels to interact, enact environmental changes, and evolve through local survival, merging, and mutation operations implemented with HyperNEAT and PyTorch. We provide an exploratory experiment implementing physics inspired by slime mold behavior showcasing the emergence of competition between sessile and mobile organisms, cycles of resource depletion and recovery, and symbiosis between diverse organisms. We conclude by outlining future work to discover simulation parameters through measures of multi-scale complexity and diversity. Code for Coralai is available at https://github.com/aidanbx/coralai , video demos are available at https://www.youtube.com/watch?v=NL8IZQY02-8 . |
| title | Coralai: Intrinsic Evolution of Embodied Neural Cellular Automata Ecosystems |
| topic | Neural and Evolutionary Computing Machine Learning Multiagent Systems |
| url | https://arxiv.org/abs/2406.09654 |