Learning to Plan
Yann discusses the challenge of enabling machines to learn predictive models that can handle the complexities and uncertainties of the real world. He emphasizes the need for effective planning systems in robotics, where understanding human behavior adds another layer of complexity. The conversation highlights the evolution of AI and the importance of developing abstract representations that machines can utilize to navigate dynamic environments.In this clip
From this podcast
Lex Fridman Podcast
Yann LeCun: Dark Matter of Intelligence and Self-Supervised Learning | Lex Fridman Podcast #258
Related Questions
How do AI systems learn dynamically?
Can we predict human actions based on the discussions in the episode Yann Lecun: Meta AI, Open Source, Limits of LLMs, AGI & the Future of AI | Lex Fridman Podcast #416 and the clip Hierarchical Planning Insights?
As we have robots interact in the physical world, is that a signal that could be used in reinforcement learning in the context of the episode Pieter Abbeel: Deep Reinforcement Learning | Lex Fridman Podcast #10 and the clip Hierarchical Reasoning Challenges?