NeuralIPS

December 11, 2018

440

NeuralIPS

Wonseok Jung

December 11, 2018

More Decks by Wonseok Jung

See All by Wonseok Jung

Ai for business -self car driving

0

230

reinforcement_learning_.pdf

2

1.8k

원석이의 모두연에서 강화학습 보석되기

0

460

Introduction Deep Reinforcement Learning

0

180

Deep reinforcemenet learning -2

0

220

Deep Reinforcement Learning - Introduction

1

680

How to become a datascientist ?

2

2.4k

Review of Taylor series

1

140

꿈꾸는 Agent

2

170

Featured

See All Featured

Writing Fast Ruby

630

63k

RailsConf & Balkan Ruby 2019: The Past, Present, and Future of Rails at GitHub

141

35k

Principles of Awesome APIs and How to Build Them.

128

18k

Documentation Writing (for coders)

77

5.5k

0

830

Avoiding the “Bad Training, Faster” Trap in the Age of AI

0

230

Designing for Timeless Needs

1

470

Mobile First: as difficult as doing things right

225

10k

Deep Space Network (abreviated)

0

300

SEOcharity - Dark patterns in SEO and UX: How to avoid them and build a more ethical web

0

270

The Mindset for Success: Future Career Progression

PRO

0

490

The Limits of Empathy - UXLibs8

1

660

Transcript

3-JOWJUFEUBML/FVSBM*14 8POTFPL+VOH
None
None
None
43࠙ীࢲ gradient descent methodۄҊ ೞ৓חؘ, gradient ascent੉׮. rewardܳ maximize ೞח
policyܳ ଺ӝ ਤ೧ࢲח gradient aascent ׮.
43࠙ীࢲ gradient descent methodۄҊ ೞ৓חؘ, gradient ascent੉׮. rewardܳ maximize ೞח
policyܳ ଺ӝ ਤ೧ࢲח gradient aascent ܳ ೧ঠೠ׮.
None
None
None
None
None