Home#

ScaRLib (Scala Reinforcement Learning Library) is a Scala-based framework for cooperative many agents reinforcement learning (CMARL).

The aim of this project is to develop a tool that relies on state-of-the-art deep learning libraries to support the definition of CMARL systems in JVM-based environments. Moreover, ScaRLib integrates ScaFi programming framework and Alchemist simulator to enable learning of field-based coordination policies for large-scale systems.

---