Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
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
150
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
190
reinforcement_learning_.pdf
wonseokjung
2
1.5k
원석이의 모두연에서 강화학습 보석되기
wonseokjung
0
410
NeuralIPS
wonseokjung
0
400
Deep reinforcemenet learning -2
wonseokjung
0
190
Deep Reinforcement Learning - Introduction
wonseokjung
1
630
How to become a datascientist ?
wonseokjung
2
2.3k
Review of Taylor series
wonseokjung
1
120
꿈꾸는 Agent
wonseokjung
2
140
Featured
See All Featured
Connecting the Dots Between Site Speed, User Experience & Your Business [WebExpo 2025]
tammyeverts
5
210
A Tale of Four Properties
chriscoyier
160
23k
The Success of Rails: Ensuring Growth for the Next 100 Years
eileencodes
45
7.4k
Designing Experiences People Love
moore
142
24k
[RailsConf 2023 Opening Keynote] The Magic of Rails
eileencodes
29
9.5k
RailsConf & Balkan Ruby 2019: The Past, Present, and Future of Rails at GitHub
eileencodes
138
34k
Into the Great Unknown - MozCon
thekraken
39
1.9k
Code Review Best Practice
trishagee
68
18k
Adopting Sorbet at Scale
ufuk
77
9.4k
Visualization
eitanlees
146
16k
Intergalactic Javascript Robots from Outer Space
tanoku
271
27k
Dealing with People You Can't Stand - Big Design 2015
cassininazir
367
26k
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