SYLGNov 12, 2020

Imposing Robust Structured Control Constraint on Reinforcement Learning of Linear Quadratic Regulator

arXiv:2011.07011v21 citations
AI Analysis

This work addresses robustness and structural constraints in control systems for cyber-physical applications, representing an incremental advancement by combining existing RL and control methods.

The paper tackles the problem of learning structured feedback control for linear dynamic systems with unknown state matrices to ensure robustness against exogenous inputs, achieving this by integrating reinforcement learning with control-theoretic guarantees and validating results in a simulation with 6 agents.

This paper discusses learning a structured feedback control to obtain sufficient robustness to exogenous inputs for linear dynamic systems with unknown state matrix. The structural constraint on the controller is necessary for many cyber-physical systems, and our approach presents a design for any generic structure, paving the way for distributed learning control. The ideas from reinforcement learning (RL) in conjunction with control-theoretic sufficient stability and performance guarantees are used to develop the methodology. First, a model-based framework is formulated using dynamic programming to embed the structural constraint in the linear quadratic regulator (LQR) setting along with sufficient robustness conditions. Thereafter, we translate these conditions to a data-driven learning-based framework - robust structured reinforcement learning (RSRL) that enjoys the control-theoretic guarantees on stability and convergence. We validate our theoretical results with a simulation on a multi-agent network with 6 agents.

Foundations

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

Your Notes