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
TensorFlow & DeepMind Lab & UNREAL
Search
Kosuke Miyoshi
April 20, 2017
Technology
1
2.6k
TensorFlow & DeepMind Lab & UNREAL
TensorFlowで実装したUNREALアルゴリズムでDeepMind Labの3D迷路を解く
Kosuke Miyoshi
April 20, 2017
Tweet
Share
More Decks by Kosuke Miyoshi
See All by Kosuke Miyoshi
Representation Learning with Contrastive Predictive Coding
miyosuda
1
210
Sutton "Reinforcement Learning" 2nd Edition Ch13: Policy Gradient Methods
miyosuda
0
200
Sutton "Reinforcement Learning" 2nd Edition Ch7: n-step Bootstrapping
miyosuda
0
89
Sutton "Reinforcement Learning" 2nd Edition Ch6: TD-learning
miyosuda
0
100
SCAN
miyosuda
0
830
Variational Auto Encoderでの Disentangled表現
miyosuda
0
630
Other Decks in Technology
See All in Technology
Master Dataグループ紹介資料
sansan33
PRO
1
4.2k
AWS re:Inventre:cap ~AmazonNova 2 Omniのワークショップを体験してきた~
nrinetcom
PRO
0
130
[PR] はじめてのデジタルアイデンティティという本を書きました
ritou
1
790
AIエージェントを5分で一気におさらい!AIエージェント「構築」元年に備えよう
yakumo
1
140
田舎で20年スクラム(後編):一個人が企業で長期戦アジャイルに挑む意味
chinmo
1
1.3k
BidiAgent と Nova 2 Sonic から考える音声 AI について
yama3133
2
150
純粋なイミュータブルモデルを設計してからイベントソーシングと組み合わせるDeciderの実践方法の紹介 /Introducing Decider Pattern with Event Sourcing
tomohisa
1
830
Introduction to Sansan Meishi Maker Development Engineer
sansan33
PRO
0
330
Introduction to Bill One Development Engineer
sansan33
PRO
0
340
あの夜、私たちは「人間」に戻った。 ── 災害ユートピア、贈与、そしてアジャイルの再構築 / 20260108 Hiromitsu Akiba
shift_evolve
PRO
0
510
Sansan Engineering Unit 紹介資料
sansan33
PRO
1
3.6k
kintone開発のプラットフォームエンジニアの紹介
cybozuinsideout
PRO
0
470
Featured
See All Featured
Discover your Explorer Soul
emna__ayadi
2
1k
Abbi's Birthday
coloredviolet
0
4.2k
Ecommerce SEO: The Keys for Success Now & Beyond - #SERPConf2024
aleyda
1
1.8k
Six Lessons from altMBA
skipperchong
29
4.1k
Fantastic passwords and where to find them - at NoRuKo
philnash
52
3.5k
Exploring the relationship between traditional SERPs and Gen AI search
raygrieselhuber
PRO
2
3.5k
No one is an island. Learnings from fostering a developers community.
thoeni
21
3.6k
Agile that works and the tools we love
rasmusluckow
331
21k
Become a Pro
speakerdeck
PRO
31
5.8k
A brief & incomplete history of UX Design for the World Wide Web: 1989–2019
jct
1
270
Future Trends and Review - Lecture 12 - Web Technologies (1019888BNR)
signer
PRO
0
3.1k
Test your architecture with Archunit
thirion
1
2.1k
Transcript
5FOTPS'MPX %FFQNJOE-BC OBSSBUJWFOJHIUTגࣜձࣾ ࡾ߁༞ 5FOTPS'MPX6TFS(SPVQ
%FFQ.JOE-BC
6/3&"- ڧԽֶशͷ"$ΞϧΰϦζϜΛϕʔεʹ&YQFSJFODF 3FQMBZΛͬͨิॿλεΫΛΈ߹Θͤͯ%໎࿏Ͱ YഒͷֶशͷߴԽΛ࣮ݱ REINFORCEMENT LEARNING WITH UNSUPERVISED AUXILIARY TASKS
Max Jaderberg, Volodymyr Mnih, Wojciech Marian Czarnecki et. al (DeepMind, 2016)
ಈͷເ w ಈເͷதͰܦݧͨ͠ग़དྷࣄΛ࠶ݱ ϦϓϨΠ ͠ ͳ͕Βւഅ৽ൽ࣭ͷهԱͷݻఆΛߦ͍ͬͯΔ w ߠఆత൱ఆతͳใुʹؔΘΔग़དྷࣄͷເΛಘʹස ൟʹݟֶͯशΛߦ͍ͬͯΔ w
FYʮਫҿΈͰϥΠΦϯΛݟ͔͚ͯةݥͳʹ͋ͬ ͨʯ w 6/3&"-Ͱ͜ΕΛώϯτʹ͍ͯ͠Δ
ڧԽֶश ڥ ΤʔδΣϯτ "DUJPO ⬆ ➡ ⬇ ঢ়ଶ T ใु
S
6/3&"-ͷྲྀΕ %2/ "$ 6/3&"-
"$ "TZODISPOPVT"EWBODFE"DUPS$SJUJD w ෳͷڥΛඇಉظʹฒྻʹಈֶ͔ͯ͠शΛߴԽ ҆ఆԽͤͨ͞
К 1PMJDZ 7 ֤"DUJPOΛऔΔ֬ ݱࡏͷঢ়ଶՁ ⬆ ➡ ⬇ TPGUNBY MJOFBS
$POW $POW '$ -45. "$ͷωοτϫʔΫߏ
֤-PDBM/FUXPSLͰɺֶश݁Ռͷޯ EВ ͷΈΛٻΊɺ ΣΠτʹөͤͣ(MPCBMͷΣΠτ В ʹݸผʹөɻ (MPCBMͷΣΠτΛ·֤ͨ-PDBMͷΣΠτʹίϐʔɻ EВ EВ EВ
EВ В ʜ
1PMJDZ К 7ͷޯ R= = = w 73ʹ͚ۙͮΔ༷ʹߋ৽ w 37͕ਖ਼ͳΒɺऔͬͨBDUJPO͕ग़Δ֬Λ૿༷͢ʹߋ৽
37͕ෛͳΒɺऔͬͨBDUJPO͕ग़Δ֬ΛݮΒ༷͢ʹߋ৽ V network: Policy network: ˞্هͷදهͰ7(SBEJFOU%FTDFOU 1PMJDZ(SBEJFOU"TDFOUθv = θv - α * dθv, θ = θ + α * dθ 1PMJDZ 7
6/3&"- w "$ʹɺ&YQFSJFODF3FQMBZΛޮՌతʹͬͨิ ॿλεΫΛಋೖ͠ɺ͞ΒʹֶशΛߴԽͤ͞Δ w 1JYFM$POUSPM w 3FXBSE1SFEJDUJPO w 7BMVF'VODUJPO3FQMBZ
6/TVQFSWJTFE3&JOGPSDFNFOU"VYJMJBSZ-FBSOJOH
&YQFSJFODF3FQMBZ w <ঢ়ଶ "DUJPO ใु ࣍ঢ়ଶ>ͷϖΞΛେྔʹอଘ͠ ͯɺ͔ͦ͜ΒαϯϓϦϯάͯ͠ωοτϫʔΫΛֶश w %2/ɺ͜Ε͕ͳ͍ͱֶश͕҆ఆ͠ͳ͔ͬͨ w
"$Ͱ͍ͬͯͳ͍
None
1JYFM$POUSPM w ը໘ͷϐΫηϧͷมԽྔΛΑΓେ͖͘͢Δ༷ʹ͞ ͍ͤͨ w ը໘ͷϐΫηϧͷมԽΛٖࣅใुͱ͢Δิॿλε Ϋ
1JYFM$POUSPM w ը໘ΛYͷϐΫηϧάϦουʹ͚ɺάϦουຖʹ2ֶशΛߦ͏ w %VFMJOH/FUXPSLΛͬͨ2ֶश ˞1JYFM$POUSPMͰಘΒΕͨ2͕BDUJPOͷબʹΘΕΔ༁Ͱͳ͍ YͷάϦου BDUJPO ֤άϦουͷϐΫηϧมԽྔฏۉΛใुͱͨ࣌͠ͷׂҾՃࢉใु߹ܭ2
3FXBSE1SFEJDUJPO w &YQFSJFODF3FQMBZ͔Β࿈ଓͨ͠ϑϨʔϜऔΓग़ ͠ɺϑϨʔϜͷใु͕ɺਖ਼͔ෛ͔θϩ͔Λ༧ଌ ͢ΔิॿλεΫ w ༧ଌ͢Δใुɺ ʴ ʔPSͷൺ͕ʹͳΔ༷ʹαϯϓϦϯά ༗ӹͳใुΠϕϯτϨΞͰ͋ͬͯɺසൟʹαϯϓϦϯά͞ΕΔ
3FXBSE1SFEJDUJPO ࣍ͷใु͕ PSPSΛ༧ଌ
7BMVF'VODUJPO3FQMBZ w "$Ͱ͍ͬͯΔɺঢ়ଶՁ 7 ͷਪఆ "DUPS$SJUJDͷ$SJUJDଆ Λɺ&YQFSJFODF3FQMBZ͔ΒαϯϓϦϯάͨ͠ϑϨʔϜͰ࠶ ߦ͏ w 3FXBSE1SFEJDUJPOͱҧͬͯɺαϯϓϦϯάಛʹภΒͤͳ͍
ิॿλεΫɺ"DUJPOબʹӨڹ༩͑ͳ͍͕ɺϕʔ εͷ"$ͱ$POWɺ-45.ͷ8FJHIUΛڞ༗͍ͯ͠Δͷ ͰɺิॿλεΫΛೖΕΔ͜ͱʹΑΓɺͦΕΛղ͘ޮՌతͳ ಛදݱ͕ಘΒΕΔ͜ͱʹΑΓɺؒతʹ"DUJPOબʹӨ ڹΛ༩͑Δ
ଛࣦؔ #BTF"$ 7BMVF'VODUJPO 3FQMBZ 1JYFM$POUSPM YάϦου 3FXBSE 1SFEJDUJPO
None
"$ͱͷൺֱ %FFQ.JOE-BCڥʹͯฏۉͰYഒͷߴԽ
ΓΜ͝ΛऔΔͱ ϫʔϓʹ౸ୡ͢Δͱ ΛಘͯϥϯμϜͳ ॴʹϫʔϓ
࠶ݱݕূಈը IUUQTZPVUVCFY),R#F)* ˞4QFBLFS%FDLͰද͍ࣔͯ͠Δ߹ɺ63-ϦϯΫ͕ΫϦοΫͰ͖ͳ͍ͷͰɺQEGΛμϯϩʔυͯ͠ΫϦοΫ͍ͯͩ͘͠͞
1JYFM$POUSPM ֤άϦουͷલϑϨʔϜͱͷ ϐΫηϧมԽྔ ֤άϦουͷ2 औͬͨ"DUJPOʹର͢Δ2
1PMJDZ К ֤ΞΫγϣϯΛऔΔ֬ લਐ ޙୀ ࠨӈճస ࠨӈεϥΠυ ֶश͕ਐΉͱ΄΅ͷ֬Ͱ֤"DUJPOΛબͿΑ͏ʹͳͬͯ͘Δ
7BMVF'VODUJPO ݱࡏͷঢ়ଶՁ ϫʔϓ ʹۙͮ͘ʹͭΕ্͕͍ͯͬͯ͘
3FXBSE1SFEJDUJPO ϓϥεใु͕དྷΔͱ༧ଌ͍ͯ͠Δ
4PVSDF w IUUQTHJUIVCDPNNJZPTVEBVOSFBM