OPENBOX aims at bringing an easier understanding of open problems that helps in finding solutions for such problems. For the said purpose, I interview researchers and practitioners who have published works on open problems in various areas of Artificial Intelligence and Machine Learning to collect a simplified understanding of these open problems. These are published as podcast series.

Ideas emerge when curiosity meets clarity. Here we go with OPENBOX to bring clarity to those curious minds looking to solve real-world problems. 

This project is done in collaboration with ForHumanity. ForHumanity is a 501(c)(3) nonprofit organization dedicated to minimizing the downside risks of AI and autonomous systems. ForHumanity develops criteria for an independent audit of AI systems. To know more, visit https://forhumanity.center/. 

Today, we have Raghu with us. Raghu is a Ph.D. student at the Machine Learning Group at the Univerity of Freiburg, under the supervision of Frank Hutter. He is working on automating hyperparameter optimization for RL, AutoRL. His master's thesis was on Reinforcement learning. Artificial General Intelligence is an area of interest to him in the long term. He is also exploring Dynamic Algorithm configuration (Controlling hyperparameter dynamically). We will cover a paper titled “Automated Reinforcement Learning (AutoRL): A Survey and Open Problems” published in June 2022, which he co-authored. 

This is part 2 of the discussion. In this part, he covers the open issues in Evolutionary approaches, Meta gradient for online tuning and Blackbox online tuning.