September 5, 2022
16:00 (IST, UTC+03:00)
Guy Barash
Qaui.MD
Broadly applicable targeted data sample omission attacks
https://arxiv.org/abs/2105.01560
Presentation:
Recording:
December 5, 2022
Gera Weiss
Achiya Elyasaf
Ben-Gurion University,
Israel
Towards better interoperability between Software and AI
Abstract & Bio
January 9, 2023
Guy Katz
The Hebrew University
of Jerusalem,
Israel
Constrained Reinforcement Learning for Robotics via Scenario-Based Programming
Abstract We presents a novel technique for incorporating domain-expert knowledge into a constrained DRL training loop.
Our technique exploits the scenario-based programming paradigm, which is designed to allow specifying such knowledge in a simple and intuitive way.
Our experiments demonstrate that using our approach to leverage expert knowledge dramatically improves the safety and the performance of the agent
https://arxiv.org/abs/2206.09603
Recording: