Timezone: »

Logarithmic Regret Bound in Partially Observable Linear Dynamical Systems
Sahin Lale · Kamyar Azizzadenesheli · Babak Hassibi · Anima Anandkumar

Mon Dec 07 09:00 PM -- 11:00 PM (PST) @ Poster Session 0 #173
We study the problem of system identification and adaptive control in partially observable linear dynamical systems. Adaptive and closed-loop system identification is a challenging problem due to correlations introduced in data collection. In this paper, we present the first model estimation method with finite-time guarantees in both open and closed-loop system identification. Deploying this estimation method, we propose adaptive control online learning (AdapOn), an efficient reinforcement learning algorithm that adaptively learns the system dynamics and continuously updates its controller through online learning steps. AdapOn estimates the model dynamics by occasionally solving a linear regression problem through interactions with the environment. Using policy re-parameterization and the estimated model, AdapOn constructs counterfactual loss functions to be used for updating the controller through online gradient descent. Over time, AdapOn improves its model estimates and obtains more accurate gradient updates to improve the controller. We show that AdapOn achieves a regret upper bound of $\text{polylog}\left(T\right)$, after $T$ time steps of agent-environment interaction. To the best of our knowledge, AdapOn is the first algorithm that achieves $\text{polylog}\left(T\right)$ regret in adaptive control of \textit{unknown} partially observable linear dynamical systems which includes linear quadratic Gaussian (LQG) control.

Author Information

Sahin Lale (California Institute of Technology)
Kamyar Azizzadenesheli (Caltech)
Babak Hassibi (Caltech)
Anima Anandkumar (NVIDIA / Caltech)

Anima Anandkumar is a Bren professor at Caltech CMS department and a director of machine learning research at NVIDIA. Her research spans both theoretical and practical aspects of large-scale machine learning. In particular, she has spearheaded research in tensor-algebraic methods, non-convex optimization, probabilistic models and deep learning. Anima is the recipient of several awards and honors such as the Bren named chair professorship at Caltech, Alfred. P. Sloan Fellowship, Young investigator awards from the Air Force and Army research offices, Faculty fellowships from Microsoft, Google and Adobe, and several best paper awards. Anima received her B.Tech in Electrical Engineering from IIT Madras in 2004 and her PhD from Cornell University in 2009. She was a postdoctoral researcher at MIT from 2009 to 2010, a visiting researcher at Microsoft Research New England in 2012 and 2014, an assistant professor at U.C. Irvine between 2010 and 2016, an associate professor at U.C. Irvine between 2016 and 2017 and a principal scientist at Amazon Web Services between 2016 and 2018.

More from the Same Authors