Model-Based Reinforcement Learning
Yann shares insights on training an RNN of the world versus a policy function in reinforcement learning. Yann and Yannic discuss the power of model-based reinforcement learning and the challenges of dealing with uncertainty in high dimensional continuous spaces. Yann LeCun emphasizes the potential of energy-based self-supervised learning as the basis for common sense and the specialized nature of intelligence.In this clip
From this podcast
Machine Learning Street Talk (MLST)
ICLR 2020: Yann LeCun and Energy-Based Models
Related Questions