Published multiple papers including 'SoftTreeMax: Policy Gradient via tree expansion' (ICML 2025), 'Implementing Reinforcement Learning Datacenter Congestion Control in NVIDIA NICs' (CCGrid 2023), 'On Covariate Shift of Latent Confounders in Imitation and Reinforcement Learning' (ICLR 2022). Received the 2019 AAAI Best Paper Award.
Research Experience
Senior Research Scientist at NVIDIA Research, working on RL theory and applications. Co-founded Amooka-AI, which later became Ford Motor Company’s L3 driving policy team. Worked on projects such as autonomous driving, GPU cache control, network congestion control, datacenter cooling, and smart-grid management.
Education
BSc in EE from Technion, Israel, summa cum laude; PhD from Technion as a recipient of the IBM fellowship.
Background
Research interests span both reinforcement learning (RL) theory and applications. Specializes in artificial intelligence and machine learning. Interned at Google DeepMind and IBM Research, and received the 2019 AAAI Best Paper Award.