no code implementations • 9 Mar 2024 • Joshua Yancosek, Ali Baheri
Simulation-based falsification approaches play a pivotal role in the safety verification of control systems, particularly within critical applications.
no code implementations • 24 Feb 2024 • Lunet Yifru, Ali Baheri
Reinforcement learning (RL) has revolutionized decision-making across a wide range of domains over the past few decades.
no code implementations • 18 Jan 2024 • Ali Baheri, Mykel J. Kochenderfer
This paper explores the integration of optimal transport (OT) theory with multi-agent reinforcement learning (MARL).
no code implementations • 3 Nov 2023 • Ali Baheri, Cecilia O. Alm
Contextual bandits have emerged as a cornerstone in reinforcement learning, enabling systems to make decisions with partial feedback.
no code implementations • 18 Oct 2023 • Ali Baheri
In inverse reinforcement learning (IRL), the central objective is to infer underlying reward functions from observed expert behaviors in a way that not only explains the given data but also generalizes to unseen scenarios.
no code implementations • 12 Sep 2023 • Ali Baheri
In the dynamic and uncertain environments where reinforcement learning (RL) operates, risk management becomes a crucial factor in ensuring reliable decision-making.
no code implementations • 11 May 2023 • Ali Baheri
This paper presents an approach for data-driven policy refinement in reinforcement learning, specifically designed for safety-critical applications.
no code implementations • 10 May 2023 • Ali Baheri, Mykel J. Kochenderfer
We propose a joint falsification and fidelity optimization framework for safety validation of autonomous systems.
no code implementations • 30 Apr 2023 • Lunet Yifru, Ali Baheri
We showcased our framework in grid-world environments, successfully identifying both acceptable safety constraints and RL policies while demonstrating the effectiveness of our theorems in practice.
1 code implementation • 28 Dec 2022 • Zahra Shahrooei, Mykel J. Kochenderfer, Ali Baheri
Simulation-based falsification is a practical testing method to increase confidence that the system will meet safety requirements.
no code implementations • 3 Nov 2022 • Pouria Razzaghi, Amin Tabrizian, Wei Guo, Shulu Chen, Abenezer Taye, Ellis Thompson, Alexis Bregeon, Ali Baheri, Peng Wei
Then we survey the landscape of existing RL-based applications in aviation.
no code implementations • 26 May 2022 • Kyle Hayes, Michael W. Fouts, Ali Baheri, David S. Mebane
A promising approach for scalable Gaussian processes (GPs) is the Karhunen-Lo\`eve (KL) decomposition, in which the GP kernel is represented by a set of basis functions which are the eigenfunctions of the kernel operator.
no code implementations • 9 May 2022 • Ali Baheri, Hao Ren, Benjamin Johnson, Pouria Razzaghi, Peng Wei
We present a safety verification framework for design-time and run-time assurance of learning-based components in aviation systems.
no code implementations • 7 Mar 2022 • Jared J. Beard, Ali Baheri
To address this challenge, simulation-based safety validation is employed to test the complex system.
no code implementations • 2 Jul 2020 • Ali Baheri
This paper presents a safe reinforcement learning system for automated driving that benefits from multimodal future trajectory predictions.