2020 IEEE International Symposium
on Information Theory
21-26 June 2020 • Los Angeles, California, USA
| Paper ID | T.2.1 | ||
| Paper Title | Learning a Neural-Network Controller for a Multiplicative Observation Noise System | ||
| Authors | Vignesh Subramanian, Moses Won, Gireeja Ranade, UC Berkeley, United States | ||
| Session | T.2: Information and Control | ||
| Presentation | Lecture | ||
| Track | Topics in Information Theory | ||
| Manuscript | Click here to download the manuscript | ||
| Virtual Presentation | Click here to watch in the Virtual Symposium | ||
| Abstract | We consider the stabilization of a linear control system with multiplicative observation noise. Linear strategies have been proven to be ineffective in this system, and non-linear strategies can unboundedly outperform the best linear strategies. The current best-known control strategy is hand-crafted and far from optimal. In this paper, we use neural-network-based controllers to narrow the gap between the achievability and the converse for this problem. We propose a periodic controller structure and a greedy training procedure. This enables us to train our controller on a finite horizon problem but learn strategies that outperform the best-known hand crafted strategy and also generalize, i.e. provide stabilizing control at times beyond the training horizon. Further, we show that for our periodic approach, the learned strategies display a piecewise linear structure and are well approximated by interpretable functions. | ||
Plan Ahead
2021 IEEE International Symposium on Information Theory
11-16 July 2021 | Melbourne, Victoria, Australia
