Sotabase

Career

· Assistant Professor, University of Virginia2022–
· Research Intern, DeepMind London2021–2021
· Research Intern, Microsoft Research Montreal2021–2021
· Research Intern, Microsoft Research Montreal2020–2020
· Doctor of Philosophy in Computer Science, University of Oxford2018–2022

Publications (0)

A Deeper Look at Experience Replay
arXiv.org · 2017
311
cited
GradientDICE: Rethinking Generalized Offline Estimation of Stationary Values
International Conference on Machine Learning · 2020
106
cited
Distributional Reinforcement Learning for Efficient Exploration
International Conference on Machine Learning · 2019
97
cited
DAC: The Double Actor-Critic Architecture for Learning Options
Neural Information Processing Systems · 2019
84
cited
Mlpack 3: a Fast, Flexible Machine Learning Library
Journal of Open Source Software · 2018
73
cited
Breaking the Deadly Triad with a Target Network
International Conference on Machine Learning · 2021
57
cited
Provably Convergent Two-Timescale Off-Policy Actor-Critic with Function Approximation
International Conference on Machine Learning · 2019
56
cited
Generalized Off-Policy Actor-Critic
Neural Information Processing Systems · 2019
43
cited
Mean-Variance Policy Iteration for Risk-Averse Reinforcement Learning
AAAI Conference on Artificial Intelligence · 2020
41
cited
Average-Reward Off-Policy Policy Evaluation with Function Approximation
International Conference on Machine Learning · 2021
36
cited
Deep Residual Reinforcement Learning
Adaptive Agents and Multi-Agent Systems · 2019
35
cited
QUOTA: The Quantile Option Architecture for Reinforcement Learning
AAAI Conference on Artificial Intelligence · 2018
33
cited
ACE: An Actor Ensemble Algorithm for Continuous Control with Tree Search
AAAI Conference on Artificial Intelligence · 2018
26
cited
A Survey of In-Context Reinforcement Learning
arXiv.org · 2025
20
cited
A Deep Neural Network for Modeling Music
International Conference on Multimedia Retrieval · 2015
17
cited
Mega-Reward: Achieving Human-Level Play without Extrinsic Rewards
AAAI Conference on Artificial Intelligence · 2019
17
cited
On the Convergence of SARSA with Linear Function Approximation
International Conference on Machine Learning · 2022
17
cited
Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch
Journal of machine learning research · 2021
16
cited
A Deeper Look at Discounting Mismatch in Actor-Critic Algorithms
Adaptive Agents and Multi-Agent Systems · 2020
15
cited
AlphaStar Unplugged: Large-Scale Offline Reinforcement Learning
arXiv.org · 2023
15
cited
Sotabase