Safe RL Talk: Contextual Bandits with Constraints Revisited with Prof. Xingyu Zhou

We are excited to announce a Safe Reinforcement Learning Online Seminar talk featuring Prof. Xingyu Zhou from Wayne State University. The talk, titled Contextual Bandits with Constraints Revisited: A Modular Approach with Improved Rates, will take place on August 1, 2024, at 16:00 CEST Time (Amsterdam, Berlin, Rome, Stockholm, Vienna), 07:00 California time, and 22:00 Beijing time.

Prof. Xingyu Zhou will share recent progress on contextual bandits with unknown constraints, where the learner aims to maximize the reward while guaranteeing multiple unknown constraints. The talk will focus on achieving a sublinear regret and sublinear cumulative constraint violations.

Join the talk via Zoom using the following link: https://tum-conf.zoom-x.de/j/67269576319?pwd=ubowFTwtJCpqeW7EYCb7fbfKpFgthd.1

Meeting ID: 672 6957 6319
Passcode: 903926

For more information about the Safe RL Online Seminar, visit the seminar homepage and register to receive relevant seminar information in time.