Multi-Agent Reinforcement Learning for Stochastic OSAT Dispatching: A Matched Architecture Benchmark
This is the author’s preprint version. It has not undergone journal peer review. The manuscript presents a matched stochastic benchmark of multi-agent reinforcement-learning architectures and heuristic dispatching policies for multi-stage OSAT manufacturing.
NGOC HUY Mai
· Zenodo (CERN European Organi... · 0 citations