PredPreyGrass (1.0.0)
Exploring learned cooperation, coevolution and free-riding. Learning is achieved through Multi-Agent Deep Reinforcement Learning (MADRL) in an ecological environment. The environment emits no other than sparse reproduction rewards. No reward shaping, no explicit cooperation signal.
Release Notes
First release
Associated Publications
This is a companion discussion topic for the original entry at https://www.comses.net/codebases/0c362544-c7cf-4498-b7d7-6ef8f6be5960/releases/1.0.0