no code implementations • 28 Apr 2020 • Dano Roost, Ralph Meier, Stephan Huschauer, Erik Nygren, Adrian Egli, Andreas Weiler, Thilo Stadelmann
We present preliminary results from our sixth placed entry to the Flatland international competition for train rescheduling, including two improvements for optimized reinforcement learning (RL) training efficiency, and two hypotheses with respect to the prospect of deep RL for complex real-world control tasks: first, that current state of the art policy gradient methods seem inappropriate in the domain of high-consequence environments; second, that learning explicit communication actions (an emerging machine-to-machine language, so to speak) might offer a remedy.