[CS294 Pieter Abbeel] 1. Intro

이 글은 필자가 Pieter Abbeel 의 Deep Unsupervised Learning 2020을 듣고 정리한 글입니다.

This lecture shares what is the goal, pursuit of deep unsupervised learning

By Deep Unsupervised Learning,

• Capture rich patterns in raw data with deep networks in a label-free way → But how?
  
  • Recreate raw data distribution → Generative models
  • "Puzzle" tasks that require semantic understanding → Self-supervised Learning

Yann LeCun's LeCake

• With Pure RL, predicts a scalar reward given once in a while
• Supervised Learning, predicting human-supplied data

"Pure RL" + Supervised Learning → By Unsupervised learning, the machine predicts any part of its input for any observed part

My questions

• How RL is dealt on UL?