SamuelSchmidgall/EvolutionarySelfReplication
Produce intelligence by means of natural selection without objective/reward optimization
This project explores how complex behaviors can emerge without explicit goals or rewards, similar to natural evolution. It simulates organisms that learn to survive and self-replicate by interacting with their environment, rather than optimizing for a specific score. You observe how simple entities, represented by neural networks, adapt and evolve over generations based purely on their ability to stay 'alive' and create copies of themselves.
No commits in the last 6 months.
Use this if you are a researcher or student interested in understanding the fundamental mechanisms of intelligence and emergent behavior through evolutionary processes, particularly in the context of artificial life or AI theory.
Not ideal if you are looking for a practical AI tool to solve a specific problem with a predefined objective, like training a chatbot or optimizing a trading strategy.
Stars
15
Forks
1
Language
Python
License
MIT
Category
Last pushed
Sep 29, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/SamuelSchmidgall/EvolutionarySelfReplication"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
trevorstephens/gplearn
Genetic Programming in Python, with a scikit-learn inspired API
google/pyglove
Manipulating Python Programs
guofei9987/scikit-opt
Genetic Algorithm, Particle Swarm Optimization, Simulated Annealing, Ant Colony Optimization...
nnaisense/evotorch
Advanced evolutionary computation library built directly on top of PyTorch, created at NNAISENSE.
esa/pagmo2
A C++ platform to perform parallel computations of optimisation tasks (global and local) via the...