OCLGOct 9, 2019

Linear-Quadratic Mean-Field Reinforcement Learning: Convergence of Policy Gradient Methods

arXiv:1910.04295v270 citations
Originality Incremental advance
AI Analysis

This provides a theoretical foundation for scalable multi-agent control, though it is incremental as it focuses on a specific linear-quadratic case.

The paper tackles the problem of reinforcement learning for many exchangeable agents interacting in a mean-field manner, such as controlling robots via a central unit, by proving the convergence of policy gradient methods in a linear-quadratic setting and establishing convergence rate bounds.

We investigate reinforcement learning in the setting of Markov decision processes for a large number of exchangeable agents interacting in a mean field manner. Applications include, for example, the control of a large number of robots communicating through a central unit dispatching the optimal policy computed by maximizing an aggregate reward. An approximate solution is obtained by learning the optimal policy of a generic agent interacting with the statistical distribution of the states and actions of the other agents. We first provide a full analysis this discrete-time mean field control problem. We then rigorously prove the convergence of exact and model-free policy gradient methods in a mean-field linear-quadratic setting and establish bounds on the rates of convergence. We also provide graphical evidence of the convergence based on implementations of our algorithms.

Foundations

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

Your Notes