Timezone: »

Multi-Agent Reinforcement Learning in Stochastic Networked Systems
Yiheng Lin · Guannan Qu · Longbo Huang · Adam Wierman

Thu Dec 09 04:30 PM -- 06:00 PM (PST) @

We study multi-agent reinforcement learning (MARL) in a stochastic 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 static, fixed and local, e.g., between neighbors in a fixed, time-invariant underlying graph. In this work, we propose a Scalable Actor Critic framework that applies in settings where the dependencies can be non-local and stochastic, and provide a finite-time error bound that shows how the convergence rate depends on the speed of information spread in the network. Additionally, as a byproduct of our analysis, we obtain novel finite-time convergence results for a general stochastic approximation scheme and for temporal difference learning with state aggregation, which apply beyond the setting of MARL in networked systems.

Author Information

Yiheng Lin (California Institute of Technology)
Guannan Qu (California Institute of Technology)
Longbo Huang (IIIS, Tsinghua Univeristy)
Adam Wierman (Caltech)

More from the Same Authors