Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Faster Reinforcement Learning via Transfer

Wonseok Jung
September 10, 2018

Faster Reinforcement Learning via Transfer

이 강의 내용은 9월 6일 Sk T-brain에서 주관한 Human.Machine. Experience Together 커퍼런스에서 John Shulman의 발표를 감명깊게 들어 만들게 되었습니다.

일정부분은 제가 추가하였지만, 대부분 John Shulman이 발표한 내용을 바탕으로 만들어졌습니다.

Wonseok Jung

September 10, 2018
Tweet

More Decks by Wonseok Jung

Other Decks in Research

Transcript

  1. TRAJECTORY REINFORCEMENT LEARNING (St , At , Rt+1 , St+1

    ) (St+1 , At+1 , Rt+2 , St+2 ) (St+2 , At+2 , Rt+3 , St+3 )
  2. HOW WE CAN ALLOW OUT A.I SYSTEM MAKE TO USE

    PRIOR KNOWLEDGE? REINFORCEMENT LEARNING https://ubisafe.org/explore/demeanure-clipart-prior-knowledge/