Embracing Novelty Search
Kenneth discusses the surprising effectiveness of novelty search over traditional objective maximization in algorithms, suggesting that rigid objectives may limit creativity. He emphasizes the potential for unexpected and interesting outcomes when algorithms are allowed to explore freely. Jon adds that the vast space of possible interesting outcomes far exceeds the limited objectives we often set, highlighting the value of following curiosity in both life and machine learning.In this clip
From this podcast
Super Data Science: ML & AI Podcast with Jon Krohn
SDS 611: Open-Ended A.I.: Practical Applications for Humans and Machines — with Kenneth Stanley
Related Questions