Sotabase

Career

· Researcher, UC Berkeley Berkeley Artificial Intelligence Research Lab (BAIR)2024–
· Researcher, UC Berkeley

Publications (68)

Improved Algorithms for Linear Stochastic Bandits
Neural Information Processing Systems · 2011
1,922
cited
Off-policy Learning with Options and Recognizers
Neural Information Processing Systems · 2005
311
cited
Sharp Convergence Rates for Langevin Dynamics in the Nonconvex Setting
arXiv.org · 2018
173
cited
Online-to-Confidence-Set Conversions and Application to Sparse Stochastic Bandits
International Conference on Artificial Intelligence and Statistics · 2012
165
cited
POLITEX: Regret Bounds for Policy Iteration using Expert Prediction
International Conference on Machine Learning · 2019
136
cited
To Believe or Not to Believe Your LLM
Neural Information Processing Systems · 2024
116
cited
Online learning for linearly parametrized control problems
2012
110
cited
Model-Free Linear Quadratic Control via Reduction to Expert Prediction
International Conference on Artificial Intelligence and Statistics · 2018
100
cited
Model Selection in Contextual Stochastic Bandit Problems
Neural Information Processing Systems · 2020
100
cited
Online Learning in Markov Decision Processes with Adversarially Chosen Transition Probability Distributions
Neural Information Processing Systems · 2013
86
cited
Regret Bounds for the Adaptive Control of Linear Quadratic Systems
Annual Conference Computational Learning Theory · 2011
78
cited
Online Least Squares Estimation with Self-Normalized Processes: An Application to Bandit Problems
arXiv.org · 2011
74
cited
Prediction with Limited Advice and Multiarmed Bandits with Paid Observations
International Conference on Machine Learning · 2014
73
cited
Offline Evaluation of Ranking Policies with Click Models
Knowledge Discovery and Data Mining · 2018
71
cited
Bootstrapping Upper Confidence Bound
Neural Information Processing Systems · 2019
64
cited
Best of both worlds: Stochastic & adversarial best-arm identification
Annual Conference Computational Learning Theory · 2018
52
cited
Evaluation and Analysis of the Performance of the EXP3 Algorithm in Stochastic Environments
European Workshop on Reinforcement Learning · 2013
52
cited
Bayesian Optimal Control of Smoothly Parameterized Systems
Conference on Uncertainty in Artificial Intelligence · 2015
48
cited
Hierarchical Reasoning Model
arXiv.org · 2025
47
cited
Linear Programming for Large-Scale Markov Decision Problems
International Conference on Machine Learning · 2014
47
cited
Sotabase
Yasin Abbasi-Yadkori | Researcher Profile | Sotabase | Sotabase