activity
20192021
most citedVerifiably Safe Off-Model Reinforcement Learning

40 citations · 41 across the 3 of their papers we have counts for

collaborators

5 papers

cs.CR2021

Relational Analysis of Sensor Attacks on Cyber-Physical Systems

Jian Xiang, Nathan Fulton, Stephen Chong

Cyber-physical systems, such as self-driving cars or autonomous aircraft, must defend against attacks that target sensor hardware. Analyzing system design can help engineers unders…

cs.AI2020

CertRL: Formalizing Convergence Proofs for Value and Policy Iteration in Coq

Koundinya Vajjha, Avraham Shinnar, Vasily Pestun +2

Reinforcement learning algorithms solve sequential decision-making problems in probabilistic environments by optimizing for long-term reward. The desire to use reinforcement learni…

cs.AI2020

Verifiably Safe Exploration for End-to-End Reinforcement Learning

Nathan Hunt, Nathan Fulton, Sara Magliacane +3

Deploying deep reinforcement learning in safety-critical settings requires developing algorithms that obey hard constraints during exploration. This paper contributes a first appro…

cs.SE20201 cited

Formal Verification of End-to-End Learning in Cyber-Physical Systems: Progress and Challenges

Nathan Fulton, Nathan Hunt, Nghia Hoang +1

Autonomous systems -- such as self-driving cars, autonomous drones, and automated trains -- must come with strong safety guarantees. Over the past decade, techniques based on forma…

cs.AI201940 cited

Verifiably Safe Off-Model Reinforcement Learning

Nathan Fulton, Andre Platzer

The desire to use reinforcement learning in safety-critical settings has inspired a recent interest in formal methods for learning algorithms. Existing formal methods for learning…