8 papers
Polynomial Constraints for Robustness Analysis of Nonlinear Systems
Neelay Junnarkar, Peter Seiler, Murat Arcak
This paper presents a framework for abstracting uncertain or non-polynomial components of dynamical systems using polynomial constraints. This enables the application of polynomial…
Synthesizing Neural Network Controllers with Closed-Loop Dissipativity Guarantees
Neelay Junnarkar, Murat Arcak, Peter Seiler
This paper presents a method to synthesize neural network controllers to maximize reward subject to the hard constraint that the feedback system of plant and controller be dissipat…
Learning Neural Network Controllers with Certified Robust Performance via Adversarial Training
Neelay Junnarkar, Yasin Sonmez, Murat Arcak
Neural network (NN) controllers achieve strong empirical performance on nonlinear dynamical systems, yet deploying them in safety-critical settings requires robustness to disturban…
Stability Margins of Neural Network Controllers
Neelay Junnarkar, Murat Arcak, Peter Seiler
We present a method to train neural network controllers with guaranteed stability margins. The method is applicable to linear time-invariant plants interconnected with uncertaintie…
Exploiting Symmetry in Dynamics for Model-Based Reinforcement Learning with Asymmetric Rewards
Yasin Sonmez, Neelay Junnarkar, Murat Arcak
Recent work in reinforcement learning has leveraged symmetries in the model to improve sample efficiency in training a policy. A commonly used simplifying assumption is that the dy…
Certifying Stability and Performance of Uncertain Differential-Algebraic Systems: A Dissipativity Framework
Emily Jensen, Neelay Junnarkar, Murat Arcak +2
This paper presents a novel framework for characterizing dissipativity of uncertain systems whose dynamics evolve according to differential-algebraic equations. Sufficient conditio…