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

NeuralIPS

Avatar for Wonseok Jung Wonseok Jung
December 11, 2018
0
410

 NeuralIPS

Avatar for Wonseok Jung

Wonseok Jung

December 11, 2018
Tweet

More Decks by Wonseok Jung

See All by Wonseok Jung
Ai for business -self car driving
Avatar for Wonseok Jung wonseokjung
0
200
reinforcement_learning_.pdf
Avatar for Wonseok Jung wonseokjung
2
1.5k
원석이의 모두연에서 강화학습 보석되기
Avatar for Wonseok Jung wonseokjung
0
420
Introduction Deep Reinforcement Learning
Avatar for Wonseok Jung wonseokjung
0
160
Deep reinforcemenet learning -2
Avatar for Wonseok Jung wonseokjung
0
200
Deep Reinforcement Learning - Introduction
Avatar for Wonseok Jung wonseokjung
1
640
How to become a datascientist ?
Avatar for Wonseok Jung wonseokjung
2
2.3k
Review of Taylor series
Avatar for Wonseok Jung wonseokjung
1
120
꿈꾸는 Agent
Avatar for Wonseok Jung wonseokjung
2
150

Featured

See All Featured
Bootstrapping a Software Product
Avatar for Garrett Dimon garrettdimon
PRO
307
110k
For a Future-Friendly Web
Avatar for Brad Frost brad_frost
180
9.9k
The Art of Programming - Codeland 2020
Avatar for Erika Heidi erikaheidi
56
14k
Context Engineering - Making Every Token Count
Avatar for Addy Osmani addyosmani
5
200
Rails Girls Zürich Keynote
Avatar for Gregor Martynus gr2m
95
14k
KATA
Avatar for Megan Lloyd mclloyd
32
15k
The Success of Rails: Ensuring Growth for the Next 100 Years
Avatar for Eileen M. Uchitelle eileencodes
46
7.6k
Sharpening the Axe: The Primacy of Toolmaking
Avatar for Bryan Cantrill bcantrill
45
2.5k
The World Runs on Bad Software
Avatar for Brandon Keepers bkeepers
PRO
71
11k
Mobile First: as difficult as doing things right
Avatar for Swwweet swwweet
224
10k
Unsuck your backbone
Avatar for Amy Palamountain ammeep
671
58k
The MySQL Ecosystem @ GitHub 2015
Avatar for Sam Lambert samlambert
251
13k

Transcript

  1. 3-JOWJUFEUBML/FVSBM*14 8POTFPL+VOH

  2. None
  3. None
  4. None

  5. 43࠙ীࢲ gradient descent methodۄҊ ೞ৓חؘ, gradient ascent੉׮. rewardܳ maximize ೞח

    policyܳ ଺ӝ ਤ೧ࢲח gradient aascent ׮.

  6. 43࠙ীࢲ gradient descent methodۄҊ ೞ৓חؘ, gradient ascent੉׮. rewardܳ maximize ೞח

    policyܳ ଺ӝ ਤ೧ࢲח gradient aascent ܳ ೧ঠೠ׮.
  7. None
  8. None
  9. None
  10. None
  11. None