RL theory
Ilija Bogunovic
sequential decision making
robust reinforcement learning
bandits
safe decision making
Bogunovic works on algorithmic sequential decision making, robust and safe learning, and reinforcement learning with strong representation in NeurIPS, ICLR, ICML, and AISTATS venues.
Pros
- Strong robust-RL and bandit theory with an excellent NeurIPS/ICML/ICLR/AISTATS record
- UCL provides a strong ML ecosystem and visibility
- Clear sequential-decision-making and safety fit
A quick heads-up: This list is a work in progress! The focus tags and pros are AI-generated, so they might occasionally miss the mark. If you spot any missing labs, notice an error, or have ideas for improvements, please feel free to open a pull request. We’d love your help making this better!