Blind Spots in Reinforcement Learning
b'
An intelligent agent trained in a simulated environment may be prone to making mistakes in the real world due to discrepancies between the training and real-world\\xa0conditions. The areas where an agent makes mistakes are hard to find, known as "blind spots," and can stem from various reasons. In this week\\u2019s episode, Kyle is joined by Ramya Ramakrishnan, a PhD candidate at MIT, to discuss the idea \\u201cblind spots\\u201d in reinforcement learning and approaches to discover them.
'