This repository shows the application of reinforcement learning to solve a particular production logistics problem dealing with the coordination of material supply for an assembly process.
Train an ppo-agent (by default for only 10,000 steps, which should take <1min):
docker-compose up ppo-trainingTilemap-animation of the trained agent (not yet awesome after only 10k steps) (visit http://localhost:5000):
docker-compose up ppo-web-animation-tilemap(see commands in docker-compose.yml for info on which scripts are executable)