Nadav Merlis

About me

I am an assistant professor at the Faculty of Data and Decision Sciences at the Technion. My research focuses on Multi-Armed Bandit problems and other theoretical aspects in Reinforcement Learning. Before that, I was a postdoctoral fellow at CREST, ENSAE, working with Prof. Vianney Perchet. I completed my Ph.D. in 2022 at the RL^2 lab at the Technion, supervised by Prof. Shie Mannor.

Publications

On Bits and Bandits: Quantifying the Regret-Information Trade-off

Itai Shufaro, Nadav Merlis, Nir Weinberger, and Shie Mannor

ICLR, 2025 [paper]

Reinforcement Learning with Lookahead Information

Nadav Merlis

NeurIPS, 2024 [paper]

The Value of Reward Lookahead in Reinforcement Learning

Nadav Merlis, Dorian Baudry, and Vianney Perchet

NeurIPS, 2024 [paper]

Improved Algorithms for Contextual Dynamic Pricing

Matilde Tullii*, Solenne Gaucher*, Nadav Merlis, and Vianney Perchet

NeurIPS, 2024 [paper]

Multi-Armed Bandits with Guaranteed Revenue per Arm

Dorian Baudry, Nadav Merlis, Mathieu Molina, Hugo Richard, and Vianney Perchet

AISTATS, 2024 [paper]

On Preemption and Learning in Stochastic Scheduling

Nadav Merlis*, Hugo Richard*, Flore Sentenac*, Corentin Odic, Mathieu Molina, and Vianney Perchet

ICML, 2023 [paper]

Reinforcement Learning with History-Dependent Dynamic Contexts

Guy Tennenholtz*, Nadav Merlis*, Lior Shani, Martin Mladenov, and Craig Boutilier

ICML, 2023 [paper]

Reinforcement Learning with a Terminator

Guy Tennenholtz, Nadav Merlis, Lior Shani, Shie Mannor, Uri Shalit, Gal Chechik, Assaf Hallak, and Gal Dalal

NeurIPS, 2022 [paper]

Query-Reward Tradoffs in Multi-Armed Bandits

Nadav Merlis, Yonathan Efroni, and Shie Mannor

RLDM, 2022 [paper]

Confidence-Budget Matching for Sequential Budgeted Learning

Yonathan Efroni*, Nadav Merlis*, Aadirupa Saha, and Shie Mannor

ICML 2021 [paper]

Ensemble Bootstrapping for Q-Learning

Oren Peer, Chen Tessler, Nadav Merlis, and Ron Meir

ICML 2021 [paper]

Lenient Regret for Multi-Armed Bandits

Nadav Merlis and Shie Mannor

AAAI 2021 [paper]

Reinforcement Learning with Trajectory Feedback

Yonathan Efroni*, Nadav Merlis*, and Shie Mannor

AAAI 2021 [paper]

Tight Lower Bounds for Combinatorial Multi-Armed Bandits

Nadav Merlis and Shie Mannor

COLT 2020 [paper]

Tight Regret Bounds for Model-Based Reinforcement Learning with Greedy Policies

Yonathan Efroni*, Nadav Merlis*, Mohammad Ghavamzadeh, and Shie Mannor

NeurIPS 2019 [paper]

Batch-Size Independent Regret Bounds for the Combinatorial Multi-Armed Bandit Problem

Nadav Merlis and Shie Mannor

COLT 2019 [paper]

Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning

Tom Zahavy*, Matan Haroush*, Nadav Merlis*, Daniel J. Mankowitz, and Shie Mannor

NeurIPS 2018 [paper]

Preprints

Stable Matching with Ties: Approximation Ratios and Learning

Shiyun Lin, Simon Mauras, Nadav Merlis, and Vianney Perchet

Preprint, 2025 [paper]

Ranking with Popularity Bias: User Welfare under Self-Amplification Dynamics

Guy Tennenholtz, Martin Mladenov, Nadav Merlis, and Craig Boutilier

Preprint, 2024 [paper]