Real-World AI Challenges
The discussion highlights the significant barriers to applying game-based AI techniques in real-world scenarios, such as self-driving cars. Key challenges include the unpredictability of outcomes and the ambiguity of objective functions. Exciting advancements like muzero, which learns rules dynamically, signal a promising direction for future research in this area.In this clip
From this podcast
Super Data Science: ML & AI Podcast with Jon Krohn
SDS 569: A.I. For Crushing Humans at Poker and Board Games — with Noam Brown
Related Questions
What's holding back self-driving cars as discussed in the episode George Hotz: Hacking the Simulation & Learning to Drive with Neural Nets | Lex Fridman Podcast #132 and the clip Autonomous Driving Insights?
What's holding back self-driving cars as discussed in the episode George Hotz: Hacking the Simulation & Learning to Drive with Neural Nets | Lex Fridman Podcast #132 and the clip Autonomous Driving Insights?
What are some specific technical barriers to self-driving cars as discussed in the episode Chris Urmson: Self-Driving Cars at Aurora, Google, CMU, and DARPA | Lex Fridman Podcast #28 and the clip Real World Challenges?