Get started
Author

Nadav Merlis

Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning
2018 · Zahavy, Tom, Haroush, Matan, et al. · arXiv (Cornell University) · 147
PDF
Ensemble Bootstrapping for Q-Learning
2021 · Peer, Oren, Tessler, Chen, et al. · arXiv (Cornell University) · 32
PDF
Tight Regret Bounds for Model-Based Reinforcement Learning with Greedy Policies
2019 · Efroni, Yonathan, Merlis, Nadav, et al. · arXiv (Cornell University) · 24
PDF
Reinforcement Learning with Trajectory Feedback
2021 · Efroni, Yonathan, Merlis, Nadav, et al. · AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) · 23
PDF
Batch-Size Independent Regret Bounds for the Combinatorial Multi-Armed Bandit Problem
2019 · Merlis, Nadav, Mannor, Shie · arXiv (Cornell University) · 14
PDF
Reinforcement Learning with Trajectory Feedback
2021 · Yonathan Efroni, Nadav Merlis, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 12
Tight Lower Bounds for Combinatorial Multi-Armed Bandits
2020 · Merlis, Nadav, Mannor, Shie · arXiv (Cornell University) · 12
PDF
Improved Algorithms for Contextual Dynamic Pricing
2024 · Matilde Tullii, Solenne Gaucher, et al. · neural information processing systems · 10
PDF
The Value of Reward Lookahead in Reinforcement Learning
2024 · Nadav Merlis, Dorian Baudry, et al. · neural information processing systems · 6
PDF
Reinforcement Learning with Lookahead Information
2024 · Nadav Merlis · neural information processing systems · 4
PDF
Confidence-Budget Matching for Sequential Budgeted Learning
2021 · Efroni, Yonathan, Merlis, Nadav, et al. · arXiv (Cornell University) · 4
PDF
Lenient Regret for Multi-Armed Bandits
2020 · Merlis, Nadav, Mannor, Shie · arXiv (Cornell University) · 4
PDF
On Bits and Bandits: Quantifying the Regret-Information Trade-off
2024 · Shufaro, Itai, Merlis, Nadav, et al. · arXiv (Cornell University) · 3
PDF
Neural-Linear Architectures for Sequential Decision Making
2019 · Tom Zahavy, Matan Haroush, et al. · Indian Control Conference · 3
Stable Matching with Ties: Approximation Ratios and Learning
2025 · Shiyun Lin, Simon Mauras, et al. · neural information processing systems · 2
PDF
Lenient Regret for Multi-Armed Bandits
2021 · Nadav Merlis, Shie Mannor · Proceedings of the AAAI Conference on Artificial Intelligence · 2
Online Linear Regression with Paid Stochastic Features
2026 · Nadav Merlis, Kyoungseok Jang, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 1
Reinforcement Learning with Multi-Step Lookahead Information Via Adaptive Batching
2026 · Merlis, Nadav · arXiv (Cornell University) · 1
PDF
On the Hardness of Reinforcement Learning with Transition Look-Ahead
2025 · Pla, Corentin, Richard, Hugo, et al. · arXiv (Cornell University) · 1
PDF
Never Worse, Mostly Better: Stable Policy Improvement in Deep Reinforcement Learning
2023 · Pranav Khanna, Guy Tennenholtz, et al. · Adaptive Agents and Multi-Agents Systems · 1
PDF
Ranking with Popularity Bias: User Welfare under Self-Amplification Dynamics
2023 · Tennenholtz, Guy, Mladenov, Martin, et al. · arXiv (Cornell University) · 1
PDF
Reinforcement Learning with History-Dependent Dynamic Contexts
2023 · Tennenholtz, Guy, Merlis, Nadav, et al. · arXiv (Cornell University) · 1
PDF
Query-Reward Tradeoffs in Multi-Armed Bandits
2021 · Merlis, Nadav, Efroni, Yonathan, et al. · arXiv (Cornell University) · 1
PDF
Stabilizing Off-Policy Reinforcement Learning with Conservative Policy Gradients
2019 · Chen Tessler, Nadav Merlis, et al. · arXiv (Cornell University) · 1
Expected Sample Complexity in Multi-Armed Bandits
2026 · Sukenik, Nadav, Merlis, Nadav · arXiv (Cornell University)
PDF
Works count: 32
Citation count: 310
H-index: 8
I10-index: 8
Year
Topic
Type