Timezone: »
Robust online control with model misspecification
Xinyi Chen · Udaya Ghai · Elad Hazan · Alexandre Megretsky
We study online control of an unknown nonlinear dynamical system that is approximated by a time-invariant linear system with model misspecification. Our study focuses on {\bf robustness}, which measures how much deviation from the assumed linear approximation can be tolerated while maintaining a bounded L2-gain.
Some models cannot be stabilized even with perfect knowledge of their coefficients: the robustness is limited by the minimal distance between the assumed dynamics and the set of unstabilizable dynamics. Therefore it is necessary to assume a lower bound on this distance. Under this assumption, and with full observation of the $d$ dimensional state, we describe an efficient controller that attains $\Omega(\frac{1}{\sqrt{d}})$ robustness together with an L2-gain whose dimension dependence is near optimal. We also give an inefficient algorithm that attains constant robustness independent of the dimension, with a finite but sub-optimal L2-gain.
Author Information
Xinyi Chen (Google Research)
Udaya Ghai (Princeton)
Elad Hazan (Princeton University)
Alexandre Megretsky (Massachusetts Institute of Technology)
More from the Same Authors
-
2021 : A Boosting Approach to Reinforcement Learning »
Nataly Brukhim · Elad Hazan · Karan Singh -
2022 : Non-convex online learning via algorithmic equivalence »
Udaya Ghai · Zhou Lu · Elad Hazan -
2022 : Fast Convergence for Unstable Reinforcement Learning Problems by Logarithmic Mapping »
Wang Zhang · Lam Nguyen · Subhro Das · Alexandre Megretsky · Luca Daniel · Tsui-Wei Weng -
2023 Poster: ConCerNet: A Contrastive Learning Based Framework for Automated Conservation Law Discovery and Trustworthy Dynamical System Prediction »
Wang Zhang · Lily Weng · Subhro Das · Alexandre Megretsky · Luca Daniel · Lam Nguyen -
2022 Poster: A Regret Minimization Approach to Multi-Agent Control »
Udaya Ghai · Udari Madhuhshani · Naomi Leonard · Elad Hazan -
2022 Spotlight: A Regret Minimization Approach to Multi-Agent Control »
Udaya Ghai · Udari Madhuhshani · Naomi Leonard · Elad Hazan -
2021 Poster: Boosting for Online Convex Optimization »
Elad Hazan · Karan Singh -
2021 Spotlight: Boosting for Online Convex Optimization »
Elad Hazan · Karan Singh -
2021 Poster: A Regret Minimization Approach to Iterative Learning Control »
Naman Agarwal · Elad Hazan · Anirudha Majumdar · Karan Singh -
2021 Spotlight: A Regret Minimization Approach to Iterative Learning Control »
Naman Agarwal · Elad Hazan · Anirudha Majumdar · Karan Singh -
2021 Tutorial: Online and non-stochastic control »
Elad Hazan · Karan Singh -
2021 : Online and non-stochastic control »
Elad Hazan -
2020 Poster: Boosting for Control of Dynamical Systems »
Naman Agarwal · Nataly Brukhim · Elad Hazan · Zhou Lu -
2019 Poster: Efficient Full-Matrix Adaptive Regularization »
Naman Agarwal · Brian Bullins · Xinyi Chen · Elad Hazan · Karan Singh · Cyril Zhang · Yi Zhang -
2019 Poster: Online Control with Adversarial Disturbances »
Naman Agarwal · Brian Bullins · Elad Hazan · Sham Kakade · Karan Singh -
2019 Oral: Efficient Full-Matrix Adaptive Regularization »
Naman Agarwal · Brian Bullins · Xinyi Chen · Elad Hazan · Karan Singh · Cyril Zhang · Yi Zhang -
2019 Oral: Online Control with Adversarial Disturbances »
Naman Agarwal · Brian Bullins · Elad Hazan · Sham Kakade · Karan Singh -
2019 Poster: Provably Efficient Maximum Entropy Exploration »
Elad Hazan · Sham Kakade · Karan Singh · Abby Van Soest -
2019 Oral: Provably Efficient Maximum Entropy Exploration »
Elad Hazan · Sham Kakade · Karan Singh · Abby Van Soest -
2018 Poster: On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization »
Sanjeev Arora · Nadav Cohen · Elad Hazan -
2018 Oral: On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization »
Sanjeev Arora · Nadav Cohen · Elad Hazan -
2017 Poster: Efficient Regret Minimization in Non-Convex Games »
Elad Hazan · Karan Singh · Cyril Zhang -
2017 Talk: Efficient Regret Minimization in Non-Convex Games »
Elad Hazan · Karan Singh · Cyril Zhang