Deep Q-learning

Concept

An extension of Q-learning that uses deep neural networks to approximate the Q-function, enabling it to handle high-dimensional state spaces like raw pixels from games.

Mentioned in 2 videos

Videos Mentioning Deep Q-learning

MIT 6.S094: Deep Reinforcement Learning for Motion Planning

Lex Fridman

An extension of Q-learning that uses deep neural networks to approximate the Q-function, enabling it to handle high-dimensional state spaces like raw pixels from games.

Melanie Mitchell: Concepts, Analogies, Common Sense & Future of AI | Lex Fridman Podcast #61

Lex Fridman

A specific type of reinforcement learning algorithm that allowed DeepMind's AI to achieve superhuman performance in Atari games.