Timezone: »

 
Poster
Distributed Influence-Augmented Local Simulators for Parallel MARL in Large Networked Systems
Miguel Suau · Jinke He · Mustafa Mert Çelikok · Matthijs Spaan · Frans Oliehoek

Tue Nov 29 09:00 AM -- 11:00 AM (PST) @ Hall J #916
in Poster Session 1 »

Due to its high sample complexity, simulation is, as of today, critical for the successful application of reinforcement learning. Many real-world problems, however, exhibit overly complex dynamics, making their full-scale simulation computationally slow. In this paper, we show how to factorize large networked systems of many agents into multiple local regions such that we can build separate simulators that run independently and in parallel. To monitor the influence that the different local regions exert on one another, each of these simulators is equipped with a learned model that is periodically trained on real trajectories. Our empirical results reveal that distributing the simulation among different processes not only makes it possible to train large multi-agent systems in just a few hours but also helps mitigate the negative effects of simultaneous learning.

Keywords: multi-agent reinforcement learning · Influence · Simulation · state abstraction · Factorization.
[ Paper]  [ Poster]  [ OpenReview] 

Author Information

Miguel Suau (Delft University of Technology)
Jinke He (Delft University of Technology)
Mustafa Mert Çelikok (Aalto University)
Matthijs Spaan (Delft University of Technology)
Frans Oliehoek (TU Delft)

More from the Same Authors