Reproduce “Evolution of a Complex Predator-Prey Ecosystem on Large-scale Multi-Agent Deep Reinforcement Learning” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Jun Yamada, John Shawe-Taylor, Zafeirios Fountas

The authors present a grid-world simulation of more than 1,000 predator and prey agents that learn, reproduce, and, in a separate experiment, inherit physical traits. Recurrent learning guides both species. In one test, populations cycle stably, peaking at about 1,200 predators and 800 prey; another trained setting yields stable coexistence, so these simulation results do not validate real animal behavior.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.