Sotabase

Career

· Visitor/Intern, Microsoft Research
· Postdoctoral Researcher, UC Berkeley
· Master's Degree in Electrical Engineering, University of Michigan
· PhD in Computer Science, University of Washington

Publications (29)

Reward-Free RL is No Harder Than Reward-Aware RL in Linear Markov Decision Processes
International Conference on Machine Learning · 2022
57
cited
Active Learning for Identification of Linear Dynamical Systems
Annual Conference Computational Learning Theory · 2020
54
cited
First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation Approach
International Conference on Machine Learning · 2021
48
cited
Leveraging Offline Data in Online Reinforcement Learning
International Conference on Machine Learning · 2022
44
cited
Beyond No Regret: Instance-Dependent PAC Reinforcement Learning
Annual Conference Computational Learning Theory · 2021
41
cited
Instance-Dependent Near-Optimal Policy Identification in Linear MDPs via Online Experiment Design
Neural Information Processing Systems · 2022
36
cited
Steering Your Diffusion Policy with Latent Space Reinforcement Learning
arXiv.org · 2025
33
cited
ASID: Active Exploration for System Identification in Robotic Manipulation
International Conference on Learning Representations · 2024
29
cited
Best Arm Identification with Safety Constraints
International Conference on Artificial Intelligence and Statistics · 2021
24
cited
Optimal Exploration for Model-Based RL in Nonlinear Systems
Neural Information Processing Systems · 2023
23
cited
Task-Optimal Exploration in Linear Dynamical Systems
International Conference on Machine Learning · 2021
22
cited
Experimental Design for Regret Minimization in Linear Bandits
International Conference on Artificial Intelligence and Statistics · 2020
16
cited
Instance-Optimality in Interactive Decision Making: Toward a Non-Asymptotic Theory
Annual Conference Computational Learning Theory · 2023
16
cited
Active Learning with Safety Constraints
Neural Information Processing Systems · 2022
14
cited
Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL
arXiv.org · 2024
12
cited
Humor in AI: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioning
Neural Information Processing Systems · 2024
10
cited
Active learning of neural population dynamics using two-photon holographic optogenetics
arXiv.org · 2024
3
cited
Corruption-Robust Linear Bandits: Minimax Optimality and Gap-Dependent Misspecification
Neural Information Processing Systems · 2024
2
cited
Fair Active Learning in Low-Data Regimes
Conference on Uncertainty in Artificial Intelligence · 2023
2
cited
Robust Finetuning of Vision-Language-Action Robot Policies via Parameter Merging
arXiv.org · 2025
2
cited
Sotabase
Andrew Wagenmaker | Researcher Profile | Sotabase | Sotabase