LGMAMLJun 11, 2020

Multi-Agent Reinforcement Learning in Stochastic Networked Systems

arXiv:2006.06555v350 citations
Originality Incremental advance
AI Analysis

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes