Multi-Agent Reinforcement Learning in Stochastic Networked Systems
This work addresses scalability issues in MARL for networked systems, offering a method that extends beyond static dependencies, which is incremental as it builds on existing actor-critic approaches.
The paper tackles the scalability challenge in multi-agent reinforcement learning (MARL) for stochastic networked systems by proposing a Scalable Actor Critic framework that handles non-local and stochastic dependencies, providing a finite-time error bound that depends on information spread speed.
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.