no code implementations • 4 Apr 2024 • Darioush Kevian, Usman Syed, Xingang Guo, Aaron Havens, Geir Dullerud, Peter Seiler, Lianhui Qin, Bin Hu
In this paper, we explore the capabilities of state-of-the-art large language models (LLMs) such as GPT-4, Claude 3 Opus, and Gemini 1. 0 Ultra in solving undergraduate-level control problems.
no code implementations • 25 Jan 2024 • Patricia Pauli, Aaron Havens, Alexandre Araujo, Siddharth Garg, Farshad Khorrami, Frank Allgöwer, Bin Hu
However, a direct application of LipSDP to the resultant residual ReLU networks is conservative and even fails in recovering the well-known fact that the MaxMin activation is 1-Lipschitz.
1 code implementation • ICLR 2023 • Alexandre Araujo, Aaron Havens, Blaise Delattre, Alexandre Allauzen, Bin Hu
Important research efforts have focused on the design and training of neural networks with a controlled Lipschitz constant.
Ranked #1 on Provable Adversarial Defense on CIFAR-100
no code implementations • 3 Jan 2022 • Aaron Havens, Darioush Keivan, Peter Seiler, Geir Dullerud, Bin Hu
We show that the ROA analysis can be approximated as a constrained maximization problem whose goal is to find the worst-case initial condition which shifts the terminal state the most.
no code implementations • 30 Nov 2021 • Darioush Keivan, Aaron Havens, Peter Seiler, Geir Dullerud, Bin Hu
We build a connection between robust adversarial RL and $\mu$ synthesis, and develop a model-free version of the well-known $DK$-iteration for solving state-feedback $\mu$ synthesis with static $D$-scaling.
no code implementations • 5 Jun 2021 • Aaron Havens, Girish Chowdhary
As deep learning becomes more prevalent for prediction and control of real physical systems, it is important that these overparameterized models are consistent with physically plausible dynamics.
no code implementations • 24 Mar 2021 • Aaron Havens, Bin Hu
When applying imitation learning techniques to fit a policy from expert demonstrations, one can take advantage of prior stability/robustness assumptions on the expert's policy and incorporate such control-theoretic prior knowledge explicitly into the learning process.
no code implementations • 9 Dec 2019 • Aaron Havens, Yi Ouyang, Prabhat Nagarajan, Yasuhiro Fujita
The latent representation is learned exclusively from multi-step reward prediction which we show to be the only necessary information for successful planning.
Model-based Reinforcement Learning reinforcement-learning +1
no code implementations • 28 Jun 2019 • Xian Yeow Lee, Aaron Havens, Girish Chowdhary, Soumik Sarkar
Hence, it is imperative that RL agents deployed in real-life applications have the capability to detect and mitigate adversarial attacks in an online fashion.