Shield Synthesis for LTL Modulo Theories

[PDF] arxiv.org

Verification-Guided Shielding for Deep Reinforcement Learning

D Corsi, G Amir, A Rodriguez, C Sanchez… - arXiv preprint arXiv …, 2024 - arxiv.org
In recent years, Deep Reinforcement Learning (DRL) has emerged as an effective approach
to solving real-world tasks. However, despite their successes, DRL-based policies suffer …
被引用次数：2 相关文章 所有 2 个版本
[PDF] arxiv.org

Safe and Reliable Training of Learning-Based Aerospace Controllers

U Mandal, G Amir, H Wu, I Daukantas… - arXiv preprint arXiv …, 2024 - arxiv.org
In recent years, deep reinforcement learning (DRL) approaches have generated highly
successful controllers for a myriad of complex domains. However, the opaque nature of …
相关文章 所有 2 个版本
[PDF] arxiv.org

Predictable and Performant Reactive Synthesis Modulo Theories via Functional Synthesis

A Rodríguez, F Gorostiaga, C Sánchez - arXiv preprint arXiv:2407.09348, 2024 - arxiv.org
Reactive synthesis is the process of generating correct controllers from temporal logic
specifications. Classical LTL reactive synthesis handles (propositional) LTL as a …
相关文章 所有 2 个版本