Reduced-Dimensional Reinforcement Learning Control using Singular Perturbation Approximations

by   Sayak Mukherjee, et al.

We present a set of model-free, reduced-dimensional reinforcement learning (RL) based optimal control designs for linear time-invariant singularly perturbed (SP) systems. We first present a state-feedback and output-feedback based RL control design for a generic SP system with unknown state and input matrices. We take advantage of the underlying time-scale separation property of the plant to learn a linear quadratic regulator (LQR) for only its slow dynamics, thereby saving a significant amount of learning time compared to the conventional full-dimensional RL controller. We analyze the sub-optimality of the design using SP approximation theorems and provide sufficient conditions for closed-loop stability. Thereafter, we extend both designs to clustered multi-agent consensus networks, where the SP property reflects through clustering. We develop both centralized and cluster-wise block-decentralized RL controllers for such networks, in reduced dimensions. We demonstrate the details of the implementation of these controllers using simulations of relevant numerical examples and compare them with conventional RL designs to show the computational benefits of our approach.



There are no comments yet.


page 1

page 2

page 3

page 4


Hierarchical Reinforcement Learning for Optimal Control of Linear Multi-Agent Systems: the Homogeneous Case

Individual agents in a multi-agent system (MAS) may have decoupled open-...

Reinforcement Learning of Structured Control for Linear Systems with Unknown State Matrix

This paper delves into designing stabilizing feedback control gains for ...

Model-Free Optimal Control of Linear Multi-Agent Systems via Decomposition and Hierarchical Approximation

Designing the optimal linear quadratic regulator (LQR) for a large-scale...

Deep Q-learning: a robust control approach

In this paper, we place deep Q-learning into a control-oriented perspect...

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

This paper discusses learning a structured feedback control to obtain su...

Optimizing Mixed Autonomy Traffic Flow With Decentralized Autonomous Vehicles and Multi-Agent RL

We study the ability of autonomous vehicles to improve the throughput of...

Out-of-Distribution Dynamics Detection: RL-Relevant Benchmarks and Results

We study the problem of out-of-distribution dynamics (OODD) detection, w...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.