Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulator

Neural Information Processing Systems

We consider adaptive control of the Linear Quadratic Regulator (LQR), where an unknown linear system is controlled subject to quadratic costs. Leveraging recent developments in the estimation of linear systems and in robust controller synthesis, we present the first provably polynomial time algorithm that provides high probability guarantees of sub-linear regret on this problem. We further study the interplay between regret minimization and parameter estimation by proving a lower bound on the expected regret in terms of the exploration schedule used by any algorithm. Finally, we conduct a numerical study comparing our robust adaptive algorithm to other methods from the adaptive LQR literature, and demonstrate the flexibility of our proposed method by extending it to a demand forecasting problem subject to state constraints.


Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulator

arXiv.org Machine Learning

We consider adaptive control of the Linear Quadratic Regulator (LQR), where an unknown linear system is controlled subject to quadratic costs. Leveraging recent developments in the estimation of linear systems and in robust controller synthesis, we present the first provably polynomial time algorithm that provides high probability guarantees of sub-linear regret on this problem. We further study the interplay between regret minimization and parameter estimation by proving a lower bound on the expected regret in terms of the exploration schedule used by any algorithm. Finally, we conduct a numerical study comparing our robust adaptive algorithm to other methods from the adaptive LQR literature, and demonstrate the flexibility of our proposed method by extending it to a demand forecasting problem subject to state constraints.


Announcing the public preview for Adaptive Application Controls

#artificialintelligence

At Microsoft Ignite, we announced new adaptive applications controls that protect your applications from malware by using whitelisting rules. Today, we are excited to share that these capabilities are available for public preview in Azure Security Center.


Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulator

Neural Information Processing Systems

We consider adaptive control of the Linear Quadratic Regulator (LQR), where an unknown linear system is controlled subject to quadratic costs. Leveraging recent developments in the estimation of linear systems and in robust controller synthesis, we present the first provably polynomial time algorithm that provides high probability guarantees of sub-linear regret on this problem. We further study the interplay between regret minimization and parameter estimation by proving a lower bound on the expected regret in terms of the exploration schedule used by any algorithm. Finally, we conduct a numerical study comparing our robust adaptive algorithm to other methods from the adaptive LQR literature, and demonstrate the flexibility of our proposed method by extending it to a demand forecasting problem subject to state constraints.


Microsoft's New Xbox Controller Is Designed for People With Limited Mobility

TIME - Tech

Microsoft has introduced an Xbox controller designed for people with limited mobility. The Xbox Adaptive Controller is meant to take into consideration the needs of gamers who might not be able to hold typical gaming controllers for long periods of time or reach all the necessary buttons, according to a statement from Microsoft. The new controller comes as the company makes an effort to be more inclusive toward all gamers. "By taking an inclusive design approach and considerations of gamers who might not be able to reach all the bumpers and triggers or hold a controller for an extended period of time, for example, we were able to design a controller that provides a way for more fans to enjoy gaming," Xbox head Phil Spencer said in a statement. Developed in partnership with several medical organizations, including The Cerebral Palsy Foundation, along with several gamers who have limited mobility, the Xbox Adaptive Controller is made to be adaptable for each player's needs, with common adaptive switches and two large buttons that can be reprogrammed to be a standard controller button.