Goodhart's Law in Reinforcement Learning

Hal Ashton, a PhD student from the University College of London, joins us today to discuss a recent work Causal Campbell-Goodhart’s law and Reinforcement Learning. When your business is ready to make that next hire, find the right person with LinkedIn Jobs. Just visit LinkedIn.com/DATASKEPTIC to post a job for free!

Guest

Hal Ashton: Hal Ashton is a Post-Doctoral Research Associate at the Computational and Biological Learning Lab, Department of Engineering, University of Cambridge. His research focuses on algorithmic misconduct. He is interested in how emergent algorithmic crime will cause problems for society in the near future. He has conducted research at the universities of Cambridge, UCL and Oxford in topics including AI alignment, law and behavioral economics. After a career in alternative assets he now works in the regtech industry.