2 papers
cs.LG2023
Extreme Risk Mitigation in Reinforcement Learning using Extreme Value Theory
Karthik Somayaji NS, Yu Wang, Malachi Schram +4
Risk-sensitive reinforcement learning (RL) has garnered significant attention in recent years due to the growing interest in deploying RL agents in real-world scenarios. A critical…
cs.LG2023
High-Dimensional Bayesian Optimization via Semi-Supervised Learning with Optimized Unlabeled Data Sampling
Yuxuan Yin, Yu Wang, Peng Li
We introduce a novel semi-supervised learning approach, named Teacher-Student Bayesian Optimization (), integrating the teacher-student paradigm into BO to minimize…