Výsledky vyhledávání

Report

Air Traffic Controller Workload Level Prediction using Conformalized Dynamical Graph Learning

Autor: Pang, Yutian, Hu, Jueming, Lieber, Christopher S., Cooke, Nancy J., Liu, Yongming

Air traffic control (ATC) is a safety-critical service system that demands constant attention from ground air traffic controllers (ATCos) to maintain daily aviation operations. The workload of the ATCos can have negative effects on operational safety

Externí odkaz: http://arxiv.org/abs/2307.10559

Zobrazit plný text záznamu

Report

Reinforcement Learning With Reward Machines in Stochastic Games

Autor: Hu, Jueming, Gaglione, Jean-Raphael, Wang, Yanze, Xu, Zhe, Topcu, Ufuk, Liu, Yongming

We investigate multi-agent reinforcement learning for stochastic games with complex tasks, where the reward functions are non-Markovian. We utilize reward machines to incorporate high-level knowledge of complex tasks. We develop an algorithm called Q

Externí odkaz: http://arxiv.org/abs/2305.17372

Zobrazit plný text záznamu

Akademický článek

Reinforcement learning with predefined and inferred reward machines in stochastic games

Autor: Hu, Jueming, Paliwal, Yash, Kim, Hyohun, Wang, Yanze, Xu, Zhe

Publikováno v: In Neurocomputing 28 September 2024 599

Zobrazit plný text záznamu

Report

Obstacle Avoidance for UAS in Continuous Action Space Using Deep Reinforcement Learning

Autor: Hu, Jueming, Yang, Xuxi, Wang, Weichang, Wei, Peng, Ying, Lei, Liu, Yongming

Obstacle avoidance for small unmanned aircraft is vital for the safety of future urban air mobility (UAM) and Unmanned Aircraft System (UAS) Traffic Management (UTM). There are many techniques for real-time robust drone guidance, but many of them sol

Externí odkaz: http://arxiv.org/abs/2111.07037

Zobrazit plný text záznamu

Report

Decentralized Graph-Based Multi-Agent Reinforcement Learning Using Reward Machines

Autor: Hu, Jueming, Xu, Zhe, Wang, Weichang, Qu, Guannan, Pang, Yutian, Liu, Yongming

In multi-agent reinforcement learning (MARL), it is challenging for a collection of agents to learn complex temporally extended tasks. The difficulties lie in computational complexity and how to learn the high-level ideas behind reward functions. We

Externí odkaz: http://arxiv.org/abs/2110.00096

Zobrazit plný text záznamu

Report

Evaluating the Robustness of Bayesian Neural Networks Against Different Types of Attacks

Autor: Pang, Yutian, Cheng, Sheng, Hu, Jueming, Liu, Yongming

To evaluate the robustness gain of Bayesian neural networks on image classification tasks, we perform input perturbations, and adversarial attacks to the state-of-the-art Bayesian neural networks, with a benchmark CNN model as reference. The attacks

Externí odkaz: http://arxiv.org/abs/2106.09223

Zobrazit plný text záznamu