I joined Carnegie Mellon University as an Assistant Professor in the ECE department in Fall 2024, with a courtesy appointment in the MLD. I am broadly interested in Foundation Models, from theory to practice. Topics of interest include reasoning, alignment, efficiency, and optimization, among others.

​Before starting as a faculty, I was a postdoctoral scholar at UC Berkeley where I collaborated with Martin Wainwright, Peter Bartlett and Sergey Levine. Before that, I got my PhD at Stanford University where I established several fundamental results in the theory of reinforcement learning under the supervision of Emma Brunskill and Mykel J. Kochenderfer. I also had active collaborations with the labs of Microsoft Research and Facebook.

I am actively looking for strong and motivated PhD students to join our group! If you are interested in working with me, please apply to the PhD program (NOTE: If you missed the application deadline, but are still interested in a PhD position, please email me directly) and mention my name in your application. If you are an existing CMU student in any department feel free to reach out to me directly.

Postdocs: I can supervise one Postdoc starting in Fall 2026 for two years under the Carnegie Bosch Institute fellowship. Please get in touch with me prior to submitting your application at this link by the deadline January 31 at 5pm.

I am happy to host remote interns and visitors; please email me your CV and a short description of what you are interested in. I apologize I am generally unable to answer individual emails regarding PhD applications, internships, teaching or research assistantships, and general inquiries.

Current PhD Students and Close Collaborators

• Yuda Song (primary advisors Aarti Singh and J. Andrew Bagnell)
• Fahim Tajwar (primary advisors Ruslan Salakhutdinov and Jeff Schneider)
• Tong Yang (PhD, primary advisor Yuejie Chi)
• Daman Arora
• Zhaoyi Zhou
• Andy Zhou (on leave, co-founded Intology)

Former Students and Collaborators

• Gokul Swamy (CMU Robotics PhD —> ?)
• Haolun Li (Intern —> PhD at University of Illinois Urbana-Champaign)
• Yueer Zhou (Intern —> MSCS at Stanford University)
• Guanning Zeng (Intern —> PhD at CMU)
• Hyunho Kook (Intern —> PhD at University of Southern California)
• Sheikh Shafayat (Intern —> PhD at Max Planck Institute for Intelligent Systems)
• Anmol Agarwal (MS —> AI Research Scientist at Mistral AI)
• Ming Yin (Princeton Postdoc —> Assistant Professor at Georgia Tech)
• Ruiqi Zhang (Berkeley PhD —> Quant Analyst at Citadel Securities)
• Yifei Zhou (Berkeley PhD —> Member of Technical Staff at Anthropic)
• Hanshi Sun (MS —> Research Scientist at ByteDance)
• Huitao Yang (Intern —> MS at UCLA Stats)
• Jiahao Shi (Intern —> PhD at Princeton)

Foundation Models

• Fahim Tajwar*, Guanning Zeng*, Yueer Zhou, Yuda Song, Daman Arora, Yiding Jiang, Jeff Schneider, Ruslan Salakhutdinov, Haiwen Feng, Andrea Zanette
  Maximum Likelihood Reinforcement Learning [Paper][Project Website]
  Spotlight ICML 2026
  Best Paper Award ICLR 2026 SPOT Workshop
  
• Yuda Song*, Lili Chen*, Fahim Tajwar, Remi Munos, Deepak Pathak, J. Andrew Bagnell, Aarti Singh,
  Andrea Zanette
  Expanding the Capabilities of Reinforcement Learning via Text Feedback [Paper][Project Website]
  ICML 2026
  Outstanding Paper Award ICLR 2026 LLA Workshop
  Oral ICLR 2026 SPOT Workshop
  Oral ICLR 2026 MALGAI Workshop
  
• Guanning Zeng, Zhaoyi Zhou, Daman Arora, Andrea Zanette
  Shrinking the Variance: Shrinkage Baselines for Reinforcement Learning with Verifiable Rewards [Paper][Blog][Code]
  ICML 2026
  
• Sheikh Shafayat*, Fahim Tajwar*, Ruslan Salakhutdinov, Jeff Schneider, Andrea Zanette
  (* indicates equal contribution)
  Can Large Reasoning Models Self-Train? [Paper][Blog][Code]
  Under Review
  
• Daman Arora, Andrea Zanette
  Training Language Models to Reason Efficiently [Paper][Blog][Code]
  NeurIPS 2025
  
• Zhaoyi Zhou, Yuda Song, Andrea Zanette
  Accelerating Unbiased LLM Evaluation via Synthetic Feedback [Paper][Code]
  ICML 2025
  
• Hanshi Sun*, Momin Haider*†, Ruiqi Zhang*, Huitao Yang, Jiahao Qiu, Ming Yin,
  Mengdi Wang, Peter Bartlett, Andrea Zanette*
  (* indicates core authors, † rest in peace)
  Fast Best-of-N Decoding via Speculative Rejection [Paper][Blog][Code]
  NeurIPS 2024
  
• Yifei Zhou, Andrea Zanette, Jiayi Pan, Sergey Levine, Aviral Kumar
  ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL [Paper]
  ICML 2024

Foundations of RL

• Ruiqi Zhang, Andrea Zanette
  Policy Finetuning in Reinforcement Learning via Design of Experiments using Offline Data
  NeurIPS 2023 [Paper]
  
• Andrea Zanette
  When is Realizability Sufficient for Off-Policy Reinforcement Learning?
  ICML 2023 [Paper]
  
• Andrea Zanette, Martin J. Wainwright
  Bellman Residual Orthogonalization for Offline Reinforcement Learning [Paper]
  Full Oral NeurIPS 2022
  
• Andrea Zanette, Martin J. Wainwright
  Stabilizing Q-learning with Linear Architectures for Provably Efficient Learning [Paper]
  ICML (International Conference on Machine Learning), 2022
• Andrea Zanette, Martin J. Wainwright, Emma Brunskill
  Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning [Paper]
  NeurIPS 2021
  Spotlight ICML 2021 Workshop on Reinforcement Learning Theory
  
• Andrea Zanette*, Kefan Dong*, Jonathan Lee*, Emma Brunskill
  Design of Experiments for Stochastic Contextual Linear Bandits [Paper]
  NeurIPS 2021
  (* denotes equal contribution)
  
• Andrea Zanette
  Exponential Lower Bounds for Batch Reinforcement Learning:
  Batch RL can be Exponentially Harder than Online RL
  Long Oral ICML 2021 [Paper][Csaba’s Class Explanation]
  
• Andrea Zanette, Ching-An Cheng, Alekh Agarwal
  Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation,
  COLT 2021 [Paper]
  
• Andrea Zanette, Alessandro Lazaric, Mykel Kochenderfer, Emma Brunskill
  Provably Efficient Reward-Agnostic Navigation with Linear Value Iteration,
  NeurIPS 2020 [Paper]
  
• Andrea Zanette, Alessandro Lazaric, Mykel Kochenderfer, Emma Brunskill
  Learning Near Optimal Policies with Low Inherent Bellman Error
  ICML 2020 [Paper]
  
• Andrea Zanette*, David Brandfonbrener*, Emma Brunskill, Matteo Pirotta, Alessandro Lazaric
  Frequentist Regret Bounds for Randomized Least-Squares Value Iteration
  AISTATS 2020 [Paper]
  (* denotes equal contribution)
  
• Andrea Zanette, Mykel J. Kochenderfer, Emma Brunskill
  Almost Horizon-Free Structure-Aware Best Policy Identification with a Generative Model
  NeurIPS 2019 [Paper]
  
• Andrea Zanette, Alessandro Lazaric, Mykel J. Kochenderfer, Emma Brunskill
  Limiting Extrapolation in Linear Approximate Value Iteration
  NeurIPS 2019 [Paper]
  
• Andrea Zanette, Emma Brunskill
  Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function Bounds
  ICML 2019 [Paper]
  
• Andrea Zanette, Junzi Zhang, Mykel J. Kochenderfer
  Robust Super-Level Set Estimation using Gaussian Processes
  in ECML-PKDD 2018 [Paper]
  
• Andrea Zanette, Emma Brunskill
  Problem Dependent Reinforcement Learning Bounds Which Can Identify Bandit Structure in MDPs
  Long Oral ICML 2018 [Paper]
  
• Andrea Zanette, Massimiliano Ferronato, Carlo Janna
  Enriching the finite element method with meshfree techniques in structural mechanics
  in IJNME (International Journal for Numerical Methods in Engineering), 2017, [Paper]
  PAMM (Proceedings in Applied Mathematics and Mechanics), 2015, Oral
  Best Poster Award International CAE Conference 2014 [Award]
  Awarded by Advances in Engineering as key scientific article contributing to excellence in science and engineering research [Award]
  Featured in Enginsoft 2014, issue number 4 [Media]

Awards

• Nomination for ACM Doctoral Dissertation Award, 2021 (two per school)
• Nomination for AAAI/ACM SIGAI Doctoral Dissertation Award, 2021 (one per school)
• Gene Golub Dissertation Award Stanford 2021
• Foundation of Data Science (postdoctoral fellowship), 2021-2023
• Institute for the Foundations of Machine Learning (postdoctoral fellowship), 2021-2023 (declined)
• TOTAL Innovation Fellowship (industrial PhD fellowship) 2018-2020
• Key scientific article contributing to excellence in science and engineering research awarded by the committee of Advances in Engineering for the paper ‘Enriching the finite element method with mesh-free techniques in structural mechanics’
• CAE Best Poster Award, International CAE conference 2014
• Lifelong Learning Program fellowship, von Karman Institute for Fluid Dynamics, 2013
• Top score (1 / 2484 students), admission exam in the School of Engineering at the University of Padova.