Aviv Rosenberg

I am a Research Scientist at Google Research working on Reinforcement Learning applications in Large Language Models. Previously, I was an Applied Scientist at Amazon Science where I worked on recommendation systems for Alexa, and a Research Intern at Nvidia Research where I studied Reinforcement Learning with adaptive planning horizons. I obtained my PhD from the department of computer science at Tel Aviv University, where I was fortunate to have Prof. Yishay Mansour as my advisor. Prior to that, I received my Bachelor's degree in Mathematics and Computer Science from Tel Aviv University.

My primary research interest lies in theoretical and applied machine learning. More specifically, my PhD focused on data-driven sequential decision making such as  reinforcement learning, online learning and multi-armed bandit. Nowadays, I am interested in Reinforcement Learning and its applications in Large Language Models.

Publications

• Building Math Agents with Multi-Turn Iterative Preference Learning.
  Wei Xiong, Chengshuai Shi, Jiaming Shen, Aviv Rosenberg, Zhen Qin, Daniele Calandriello, Misha Khalman, Rishabh Joshi, Bilal Piot, Mohammad Saleh, Chi Jin, Tong Zhang, Tianqi Liu.
  ICLR 2025.
  [Arxiv]

• Multi-turn Reinforcement Learning from Preference Human Feedback.
  Lior Shani, Aviv Rosenberg, Asaf Cassel, Oran Lang, Daniele Calandriello, Avital Zipori, Hila Noga, Orgad Keller, Bilal Piot, Idan Szpektor, Avinatan Hassidim, Yossi Matias, Rémi Munos.
  NeurIPS 2024.
  [Arxiv]

• Warm-up Free Policy Optimization: Improved Regret in Linear Markov Decision Processes.
  Asaf Cassel, Aviv Rosenberg.
  NeurIPS 2024, EWRL 2024.
  [Arxiv]

• Online Weighted Paging with Unknown Weights.
  Orin Levy, Noam Touitou, Aviv Rosenberg.
  NeurIPS 2024.
  [Arxiv]

• Near-Optimal Regret in Linear MDPs with Aggregate Bandit Feedback.
  Asaf Cassel, Haipeng Luo, Aviv Rosenberg, Dmitry Sotnikov.
  ICML 2024.
  [Arxiv]

• Delay-Adapted Policy Optimization and Improved Regret for Adversarial MDP with Delayed Bandit Feedback.
  Tal Lancewicki, Aviv Rosenberg, Dmitry Sotnikov.
  ICML 2023.
  [Arxiv]

• A Unified Analysis of Nonstochastic Delayed Feedback for Combinatorial Semi-Bandits, Linear Bandits, and MDPs.
  Dirk van der Hoeven, Lukas Zierahn, Tal Lancewicki, Aviv Rosenberg, Nicolò Cesa-Bianchi.
  JMLR 2025, COLT 2023.
  [Arxiv]

• Planning and Learning with Adaptive Lookahead.
  Aviv Rosenberg, Assaf Hallak, Shie Mannor, Gal Chechik, Gal Dalal.
  AAAI 2023, RLDM 2022.
  [Arxiv]

• Near-Optimal Regret for Adversarial MDP with Delayed Bandit Feedback.
  Tiancheng Jin, Tal Lancewicki, Haipeng Luo, Yishay Mansour, Aviv Rosenberg.
  NeurIPS 2022, EWRL 2022, ICML 2022 Workshop on Complex Feedback in Online Learning (Oral).
  [Arxiv]

• Cooperative Online Learning in Stochastic and Adversarial MDPs.
  Tal Lancewicki, Aviv Rosenberg, Yishay Mansour.
  ICML 2022 (Oral), EWRL 2022, AAMAS 2022 Workshop on Learning with Strategic Agents (Oral).
  [Arxiv]

• Policy Optimization for Stochastic Shortest Path.
  Liyu Chen, Haipeng Luo, Aviv Rosenberg.
  COLT 2022.
  [Arxiv]

• Learning Adversarial Markov Decision Processes with Delayed Feedback.
  Tal Lancewicki, Aviv Rosenberg, Yishay Mansour.
  AAAI 2022, ICML 2021 Workshop on Reinforcement Learning Theory.
  [Arxiv]

• Minimax Regret for Stochastic Shortest Path.
  Alon Cohen, Yonathan Efroni, Yishay Mansour, Aviv Rosenberg.
  NeurIPS 2021, ICML 2021 Workshop on Reinforcement Learning Theory.
  [Arxiv]

• Oracle-Efficient Regret Minimization in Factored MDPs with Unknown Structure.
  Aviv Rosenberg, Yishay Mansour.
  NeurIPS 2021, ICML 2021 Workshop on Reinforcement Learning Theory.
  [Arxiv]

• Stochastic Shortest Path with Adversarially Changing Costs.
  Aviv Rosenberg, Yishay Mansour.
  IJCAI 2021, AAAI 2021 Workshop on Reinforcement Learning in Games.
  [Arxiv]

• Near-optimal Regret Bounds for Stochastic Shortest Path.
  Alon Cohen, Haim Kaplan, Yishay Mansour, Aviv Rosenberg.
  ICML 2020.
  [Arxiv]

• Optimistic Policy Optimization with Bandit Feedback.
  Yonathan Efroni, Lior Shani, Aviv Rosenberg, Shie Mannor.
  ICML 2020.
  [Arxiv]

• Online Stochastic Shortest Path with Bandit Feedback and Unknown Transition Function.
  Aviv Rosenberg, Yishay Mansour.
  NeurIPS 2019.
  [Arxiv]

• Online Convex Optimization in Adversarial Markov Decision Processes.
  Aviv Rosenberg, Yishay Mansour.
  ICML 2019.
  [Arxiv]

Teaching

• CS 0368-3075, Reinforcement Learning, Tel Aviv University Spring 2021 (TA).

• CS 0368-3235, Introduction to Machine Learning, Tel Aviv University Fall 2020 (TA).

• CS 0368-3235, Introduction to Machine Learning, Tel Aviv University Spring 2020 (TA).

• CS 0368-3235, Introduction to Machine Learning, Tel Aviv University Fall 2019 (TA).