Corpus ID: 219573391

Distributed Reinforcement Learning in Multi-Agent Networked Systems

@article{Lin2020DistributedRL,
  title={Distributed Reinforcement Learning in Multi-Agent Networked Systems},
  author={Yiheng Lin and Guannan Qu and Longbo Huang and Adam Wierman},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.06555}
}
  • Yiheng Lin, Guannan Qu, +1 author Adam Wierman
  • Published 2020
  • Computer Science, Mathematics
  • ArXiv
  • We study distributed reinforcement learning (RL) for a network of agents. The objective is to find localized policies that maximize the (discounted) global reward. In general, scalability is a challenge in this setting because the size of the global state/action space can be exponential in the number of agents. Scalable algorithms are only known in cases where dependencies are local, e.g., between neighbors. In this work, we propose a Scalable Actor Critic framework that applies in settings… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 46 REFERENCES