SimSpark is a generic simulator for various multiagent simulations. It supports developing physical simulations for AI and robotics research with an open-source application framework. One Simulator - Many Simulations. Simulations are created using Ruby and text-based RSG files. Different agents can participate in one simulation, connecting to SimSpark using UDP or TCP.
References in zbMATH (referenced in 1 article )
Showing result 1 of 1.
- Bianchi, Reinaldo A. C.; Celiberto, Luiz A. jun.; Santos, Paulo E.; Matsuura, Jackson P.; Lopez de Mantaras, Ramon: Transferring knowledge as heuristics in reinforcement learning: a case-based approach (2015)