Upgrade to PRO for Only $50/Year—Limited-Time Offer! 🔥
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Introduction Deep Reinforcement Learning
Search
Wonseok Jung
November 20, 2018
0
160
Introduction Deep Reinforcement Learning
Wonseok Jung
November 20, 2018
Tweet
Share
More Decks by Wonseok Jung
See All by Wonseok Jung
Ai for business -self car driving
wonseokjung
0
200
reinforcement_learning_.pdf
wonseokjung
2
1.5k
원석이의 모두연에서 강화학습 보석되기
wonseokjung
0
430
NeuralIPS
wonseokjung
0
420
Deep reinforcemenet learning -2
wonseokjung
0
200
Deep Reinforcement Learning - Introduction
wonseokjung
1
650
How to become a datascientist ?
wonseokjung
2
2.3k
Review of Taylor series
wonseokjung
1
120
꿈꾸는 Agent
wonseokjung
2
150
Featured
See All Featured
Design and Strategy: How to Deal with People Who Don’t "Get" Design
morganepeng
132
19k
Improving Core Web Vitals using Speculation Rules API
sergeychernyshev
21
1.3k
Sharpening the Axe: The Primacy of Toolmaking
bcantrill
46
2.6k
For a Future-Friendly Web
brad_frost
180
10k
The Illustrated Children's Guide to Kubernetes
chrisshort
51
51k
YesSQL, Process and Tooling at Scale
rocio
174
15k
How Fast Is Fast Enough? [PerfNow 2025]
tammyeverts
3
390
StorybookのUI Testing Handbookを読んだ
zakiyama
31
6.5k
Why You Should Never Use an ORM
jnunemaker
PRO
61
9.6k
Bash Introduction
62gerente
615
210k
Building an army of robots
kneath
306
46k
Exploring the Power of Turbo Streams & Action Cable | RailsConf2023
kevinliebholz
37
6.2k
Transcript
3-9%- 8POTFPL+VOH *OUSPEVDUJPOUP3FJOGPSDFNFOU-FBSOJOH GFBUDT
8POTFPL+VOH $JUZ6OJWFSTJUZPG/FX:PSL#BSVDI$PMMFHF %BUB4DJFODF.BKPS $POOFYJPO"*'PVOEFS %FFQ-FBSOJOH$PMMFHF3FJOGPSDFNFOU-FBSOJOH3FTFBSDIFS .PEVMBCT$53--FBEFS 3FJOGPSDFNFOU-FBSOJOH 0CKFDU%FUFDUJPO
$IBUCPU (JUIVC IUUQTHJUIVCDPNXPOTFPLKVOH 'BDFCPPL IUUQTXXXGBDFCPPLDPNXTKVOH #MPH IUUQTXPOTFPLKVOHHJUIVCJP :PVUVCF IUUQTXXXZPVUVCFDPNDIBOOFM6$N5Y8,EIM8W+6GS3X
5PEBZ .BSLPWEFDJTJPOQSPDFTT ъചणޙઁ ъചणঌҊ્ܻࣁо࠙ܨ ъചणঌҊ્ܻఋੑѐਃ
.BSLPW%FDJTJPO1SPCMFN πθ (at ∣ ot ) πθ (at ∣ st
) - policy - policy ( fully observed ) st ot at - state - observation - action o1 s1 a1 o2 s2 a2 o3 s3 a3 p(st+1 ∣ st , at ) p(st+1 ∣ st , at ) .BSLPW%FDJTJPO1SPCMFN TUBUF BDUJPO SFXBSE USBOTJUJPO١ਵ۽അغחъചणীࢲࣁ࢚ਸ
3FXBSEGVODUJPOT )JHI3FXBSE ֫ࠁ࢚ উೞѱݾীب -PX3FXBSE ծࠁ࢚ ҮాࢎҊ
1PMJDZউೞѱೞѱೞח଼ण )JHI3FXBSE -PX3FXBSE 3FXBSEGVODUJPOਸా೧ण
.BSLPWDIBJO s ∈ S s T 4UBUFTQBDF 5SBOTJUJPOPQFSBUPS 4UBUFTQBDF M
= S, T
.BSLPWDIBJO HSBQIJDBMMZ →μt +1 = T→μt μt,i = p(st =
i) s1 s2 s3 p(st+1 ∣ st , at ) p(st+1 ∣ st , at ) Ti,j = p(st+1 = i ∣ st = j) TUBUFKоযਸٸTUBUFоJؼഛܫݫܼझ UJNFTUFQUীTUBUFоJੌഛܫ
.BSLPWEFDJTJPOQSPDFTT s1 a1 s2 a2 s3 p(st+1 ∣ st ,
at ) p(st+1 ∣ st , at ) s ∈ S s A T a ∈ A 4UBUFTQBDF "DUJPOTQBDF 5SBOTJUJPOPQFSBUPS 4UBUFTQBDF "DUJPOTQBDF M = {S, A, T, r} r 3FXBSEGVODUJPO
.BSLPWEFDJTJPOQSPDFTT μt,i = p(st = i) Ti,j,k = p(st+1 =
i ∣ st = j, at = k) UJNFTUFQUীTUBUFоJੌഛܫ UJNFTUFQUীࢲTUBUFоKҊBDUJPOLੌ⮶ UJNFTUFQU ীࢲTUBUFоJੌഛܫ ξt,k = p(at = k) UJNFTUFQUীBDUJPOLੌഛܫ r : SxA → R SFXBSEGVODUJPO μt,i = ∑ j,k Ti,j,k μt,j ξt,k
1BSUJBM0CTFSWFE.BSLPWEFDJTJPOQSPDFTT s ∈ S s A T a ∈ A
4UBUFTQBDF "DUJPOTQBDF 5SBOTJUJPOPQFSBUPS 4UBUFTQBDF "DUJPOTQBDF M = {S, A, O, T, E, r} O 0CTFSWBUJPOTQBDF E &NJTTJPOQSPCBCJMJUZ P(ot ∣ st ) r 3FXBSEGVODUJPO o ∈ O PCTFSWBUJPOTQBDF o1 s1 a1 o2 s2 a2 o3 s3 a3 p(st+1 ∣ st , at ) p(st+1 ∣ st , at )
5IFHPBMPGSFJOGPSDFNFOUMFBSOJOH πθ (a ∣ s) θ ੋҕन҃ݎXFJHIUT 1PMJDZחۄݫఠܳ߸ೠ θ ੋҕन҃ݎੑ۱ਵ۽TUBUFܳ߉ҊBDUJPOਸ۱ೠ
ജ҃BDUJPOਸੑ۱ਵ۽߉ҊTUBUFܳ۱ೠ
5IFHPBMPGSFJOGPSDFNFOUMFBSOJOH pθ (s1 , a1 , . . . .
. , ST , aT ) = p(s1 ) T ∏ t=1 πθ (at ∣ st )p(st+1 ∣ st , at ) pθ (τ) θ* = argmaxθ Eτ pθ (τ) [∑ t r(st , at )]
5IFBOBUPNZPGBSFJOGPSDFNFOUMFBSOJOHBMHPSJUIN 1PMJDZܳࢎਊೞৈ ࢠࢤࢿ SFUVSOчਸஏ SFUVSO SFXBSE ܳਊೞৈ଼
সؘ
2GVODUJPOBOE7BMVFGVODUJPO Qπ(st , at ) = ∑T t′=t Eπθ [r(s′
t , a′ t ) ∣ st , at ] 2GVODUJPO 4UBUFU BDUJPOUীࢲࠗఠզٸө 5 ߉ਸࣻח୨SFXBSEӝчਸ҅
2GVODUJPOBOE7BMVFGVODUJPO 7BMVFGVODUJPO Vπ(st ) = T ∑ t′=t Eπθ [r(s′
t , a′ t ) ∣ st ] TUBUFUীࢲࠗఠզٸө 5 ߉ਸࣻח୨SFXBSEӝчਸ҅
5ZQFPG3-BMHPSJUINT 1PMJDZHSBEJFOUT 7BMVFCBTFE "DUPSDSJUJD .PEFMCBTFE3-
ъചणঌҊ્ܻ݆ਬ ਃೠࢠ ೞಌۄݫఠ উࢿ $POWFSHF
.%1 4UPDIBTUJD %FUFSNJOJTUJD $POUJOVPVT %JTDSFUF .%1ೠ ޖೠ
/&95DIBQUFS 1PMJDZHSBEJFOUT