Sotabase

Career

· Assistant Professor, Carnegie Mellon University2024–
· Postdoctoral Scholar in Electrical Engineering and Computer Sciences, UC Berkeley2024–
· PhD Graduate, Stanford University

Publications (22)

Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function Bounds
International Conference on Machine Learning · 2019
300
cited
Learning Near Optimal Policies with Low Inherent Bellman Error
International Conference on Machine Learning · 2020
235
cited
Frequentist Regret Bounds for Randomized Least-Squares Value Iteration
International Conference on Artificial Intelligence and Statistics · 2019
142
cited
Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning
Neural Information Processing Systems · 2021
132
cited
Exponential Lower Bounds for Batch Reinforcement Learning: Batch RL can be Exponentially Harder than Online RL
International Conference on Machine Learning · 2020
75
cited
Provably Efficient Reward-Agnostic Navigation with Linear Value Iteration
Neural Information Processing Systems · 2020
65
cited
Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation
Annual Conference Computational Learning Theory · 2021
57
cited
Almost Horizon-Free Structure-Aware Best Policy Identification with a Generative Model
Neural Information Processing Systems · 2019
37
cited
Robust Super-Level Set Estimation using Gaussian Processes
ECML/PKDD · 2018
33
cited
Limiting Extrapolation in Linear Approximate Value Iteration
Neural Information Processing Systems · 2019
27
cited
Can Large Reasoning Models Self-Train?
arXiv.org · 2025
24
cited
Design of Experiments for Stochastic Contextual Linear Bandits
Neural Information Processing Systems · 2021
20
cited
Problem Dependent Reinforcement Learning Bounds Which Can Identify Bandit Structure in MDPs
International Conference on Machine Learning · 2018
17
cited
When is Realizability Sufficient for Off-Policy Reinforcement Learning?
International Conference on Machine Learning · 2022
16
cited
Policy Finetuning in Reinforcement Learning via Design of Experiments using Offline Data
Neural Information Processing Systems · 2023
10
cited
Bellman Residual Orthogonalization for Offline Reinforcement Learning
Neural Information Processing Systems · 2022
8
cited
Information Directed reinforcement learning
2017
5
cited
Stabilizing Q-learning with Linear Architectures for Provably Efficient Learning
International Conference on Machine Learning · 2022
5
cited
Enriching the finite element method with meshfree particles in structural mechanics
2017
2
cited
Enriching the Finite Element Method with meshfree techniques in structural mechanics
2015
Sotabase
Andrea Zanette | Researcher Profile | Sotabase | Sotabase