.png){kind=icon}
.png){kind=icon}
Return
Reinforcement Learning for Jointly Optimal Coding and Control Policies for a Controlled Markovian System Over a Communication Channel
.png){kind=icon}
PRE
AI
E
L
S
DOI：10.1109/tac.2026.3676241.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We study the problem of joint optimization involving coding and control policies for a controlled Markovian system over a finite-rate noiseless communication channel. While structural results on the optimal encoding and control have been obtained in the literature, their implementation has been prohibitive in general, except for linear models. To this end, we first develop existence, regularity, and structural properties on optimal policies, followed by rigorous approximations and reinforcement learning results. Notably, we establish near optimality of finite model approximations obtained via predictor (conditional probability on the next state realization given the information at the controller) quantization as well as sliding finite window approximations, and the convergence of a reinforcement learning algorithm to near optimality. A detailed comparison of the approximation schemes and their performance is presented. To the best of the authors’ knowledge, this is the first rigorous reinforcement learning study on jointly optimal coding and networked control with finite rate channels.
Keywords:
Networked control systems
optimal control
reinforcement learning
source coding
Journal
IF:
7
Papers:
1.3W
Citations:
6.7W
Organization
Cited Papers