Constrained Reinforcement Learning for Robotics via Scenario-Based Programming
Davide Corsi, Raz Yerushalmi, Guy Amir, Alessandro Farinelli, David Harel, Guy Katz
preprint 2022
[paper]

Verifying Learning-Based Robotic Navigation Systems
Guy Amir, Davide Corsi, Raz Yerushalmi, Luca Marzari, David Harel, Alessandro Farinelli and Guy Katz
preprint 2022
[paper] [code] [supplementary video]

Enhancing Deep Reinforcement Learning with Scenario-Based Modeling
Raz Yerushalmi, Guy Amir, Achiya Elyasaf, David Harel, Guy Katz and Assaf Marron
preprint 2022
[paper - to appear]

Dominant Toxin Hypothesis: Unravelling the Venom Phenotype Across Micro and Macroevolution
Edward G. Smith, Joachim M. Surm, Jason Macrander, Adi Simhi*, Guy Amir*, Maria Y. Sachkova, Magda Lewandowska, Adam M. Reitzel and Yehu Moran
preprint 2022
[paper]

Verification-Aided Deep Ensemble Selection
Guy Amir, Tom Zelazny, Guy Katz and Michael Schapira
Formal Methods in Computer-Aided Design (FMCAD) 2022
[paper] [code]

Neural Network Robustness as a Verification Property: A Principled Case Study
Marco Casadio, Ekaterina Komendantskaya, Mathew Daggitt, Wen Kokke, Guy Katz, Guy Amir, and Idan Refaeli
Computer Aided Verification (CAV) 2022
[paper] [code]

Scenario-Assisted Deep Reinforcement Learning
Raz Yerushalmi, Guy Amir, Achiya Elyasaf, David Harel, Guy Katz and Assaf Marron
Model-Driven Engineering and Software Development (MODELSWARD) 2022
[paper]

Towards Scalable Verification of Deep Reinforcement Learning
Guy Amir, Michael Schapira and Guy Katz
Formal Methods in Computer-Aided Design (FMCAD) 2021
[paper] [code]

An SMT-Based Approach for Verifying Binarized Neural Networks
Guy Amir, Haoze Wu, Clark Barrett and Guy Katz
Tools and Algorithms for the Construction and Analysis of Systems (TACAS) 2021
[paper] [code]

Use and Perceptions of Multi-Monitor Workstations: A Natural Experiment
Guy Amir, Ayala Prusak, Tal Reiss, Nir Zabari and Dror Feitelson
Software Engineering Research and Industrial Practice (SER & IP) 2021
[paper]