3260 papers • 126 benchmarks • 313 datasets
This task has no description! Would you like to contribute one?
(Image credit: Papersgraph)
These leaderboards are used to track progress in artificial-life-23
No benchmarks available.
Use these libraries to find artificial-life-23 models and implementations
No datasets available.
A new system of artificial life called Lenia (from Latin lenis "smooth"), a two-dimensional cellular automaton with continuous space-time-state and generalized local rule, which supports a great diversity of complex autonomous patterns or "lifeforms" bearing resemblance to real-world microscopic organisms.
The main conclusion of these experiments is that graph re writes systems which allow conflicting rewrites are better than those which don't, as concerns their artificial life properties, in contradiction with the search for good graph rewrite systems for decentralized computing.
Melting Pot 2.0 is described, which revises and expands on Melting Pot, and introduces support for scenarios with asymmetric roles, and explains how to integrate them into the evaluation protocol.
This work simulates an abstract model of adversarial relationship between predator and prey, and looks at crypsis through evolving prey camouflage patterns in competition with evolving predator vision, to help study camouflage in nature, and the perceptual phenomenon of camouflage more generally.
JohnnyVon is an implementation of self-replicating machines in continuous two-dimensional space that demonstrates that, if an arbitrary seed pattern is put in a soup of separate individual particles, the pattern will replicate by assembling the individual particles into copies of itself.
A family of safe mutation (SM) operators that facilitate exploration without dramatically altering network behavior or requiring additional interaction with the environment are proposed, which dramatically increases the ability of a simple genetic algorithm-based neuroevolution method to find solutions in high-dimensional domains that require deep and/or recurrent neural networks.
This paper proposes an approach for measuring growth of complexity of emerging patterns in complex systems such as cellular automata and demonstrates that using the proposed metric it can automatically construct computational models with emerging properties similar to those found in the Conway’s Game of Life.
Combinatory Chemistry is introduced, an Algorithmic Artificial Chemistry based on a minimalistic computational paradigm named Combinatory Logic that discovers a wide range of emergent patterns that rely on acquiring basic constituents from the environment and decomposing them in a process that is remarkably similar to biological metabolisms.
Experimental extensions of Lenia, a continuous cellular automata family capable of producing lifelike self-organizing autonomous patterns, are reported, finding new phenomena like polyhedral symmetries, individuality, self-replication, emission, growth by ingestion, and the emergence of "virtual eukaryotes" that possess internal division of labor and type differentiation.
This paper explains how unique safety problems manifest in open-ended search, and suggests concrete contributions and research questions to explore them, to inspire progress towards creative, useful, and safe open-ending search algorithms.
Adding a benchmark result helps the community track progress.