no code implementations • 13 May 2021 • Anuradha M. Annaswamy, Anubhav Guha, Yingnan Cui, Sunbochen Tang, Peter A. Fisher, Joseph E. Gaudio
AC-RL controllers are proposed for both classes of systems and shown to lead to online policies that guarantee stability using a high-order tuner and accommodate parametric uncertainties and magnitude limits on the input.
no code implementations • 30 Mar 2021 • Yingnan Cui, Joseph E. Gaudio, Anuradha M. Annaswamy
We propose two algorithms for discrete-time parameter estimation, one for time-varying parameters under persistent excitation (PE) condition, another for constant parameters under no PE condition.
no code implementations • 23 Mar 2021 • Spencer McDonald, Yingnan Cui, Joseph E. Gaudio, Anuradha M. Annaswamy
Gradient-descent based iterative algorithms pervade a variety of problems in estimation, prediction, learning, control, and optimization.
no code implementations • 23 Jun 2020 • Arnab Sarker, Peter Fisher, Joseph E. Gaudio, Anuradha M. Annaswamy
Experiments are provided to support all theoretical derivations, which show that the spectral lines-based approach outperforms the Gaussian noise-based method when unmodeled dynamics are present, in terms of both parameter estimation error and Regret obtained using the parameter estimates with a Linear Quadratic Regulator in feedback.
no code implementations • 4 May 2020 • Joseph E. Gaudio, Anuradha M. Annaswamy, José M. Moreu, Michael A. Bolender, Travis E. Gibson
Recently, connections with variational approaches have led to the derivation of new learning algorithms with accelerated learning guarantees.
no code implementations • 10 Nov 2019 • Joseph E. Gaudio, Anuradha M. Annaswamy, Eugene Lavretsky, Michael A. Bolender
The main feature of this algorithm is a matrix of time-varying learning rates, which enables parameter estimation error trajectories to tend exponentially fast towards a compact set whenever excitation conditions are satisfied.
no code implementations • 11 Apr 2019 • Joseph E. Gaudio, Travis E. Gibson, Anuradha M. Annaswamy, Michael A. Bolender, Eugene Lavretsky
This paper demonstrates many immediate connections between adaptive control and optimization methods commonly employed in machine learning.
no code implementations • 12 Mar 2019 • Joseph E. Gaudio, Travis E. Gibson, Anuradha M. Annaswamy, Michael A. Bolender
This variational perspective includes higher order learning concepts and normalization, both of which stem from adaptive control, and allows stability to be established for dynamical machine learning problems where time-varying features are present.