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

DeepRacer DeepDive

Sponsored · Your Podcast. Everywhere. Effortlessly. Share. Educate. Inspire. Entertain. You do you. We'll handle the rest. →
Avatar for jogannaoki jogannaoki
December 05, 2018
0
990

DeepRacer DeepDive

Avatar for jogannaoki

jogannaoki

December 05, 2018
Tweet

More Decks by jogannaoki

See All by jogannaoki
エンジニアの越境
Avatar for jogannaoki jogannaoki
0
5.9k
[re:Growth 2019] Fargate for EKS
Avatar for jogannaoki jogannaoki
0
1.1k
Kubernetesを使うことによるメリットと注意点
Avatar for jogannaoki jogannaoki
0
2.1k
Developers.IO 2018 BaaSでゲームインフラをスピード構築
Avatar for jogannaoki jogannaoki
1
910

Featured

See All Featured
The Director’s Chair: Orchestrating AI for Truly Effective Learning
Avatar for Mike Taylor tmiket
1
96
Scaling GitHub
Avatar for Zach Holman holman
464
140k
For a Future-Friendly Web
Avatar for Brad Frost brad_frost
182
10k
Public Speaking Without Barfing On Your Shoes - THAT 2023
Avatar for David Neal reverentgeek
1
300
Distributed Sagas: A Protocol for Coordinating Microservices
Avatar for Caitie McCaffrey caitiem20
333
22k
Practical Tips for Bootstrapping Information Extraction Pipelines
Avatar for Matthew Honnibal honnibal
25
1.7k
Everyday Curiosity
Avatar for Cassini Nazir cassininazir
0
130
Visual Storytelling: How to be a Superhuman Communicator
Avatar for David Neal reverentgeek
2
430
Exploring the relationship between traditional SERPs and Gen AI search
Avatar for Ray Grieselhuber raygrieselhuber
PRO
2
3.6k
Statistics for Hackers
Avatar for Jake VanderPlas jakevdp
799
230k
Raft: Consensus for Rubyists
Avatar for Patrick Van Stee vanstee
141
7.3k
The Success of Rails: Ensuring Growth for the Next 100 Years
Avatar for Eileen M. Uchitelle eileencodes
47
7.9k

Transcript

  1. Naoki Jogan 1 Classmethod, Inc. AWS Business Unit Consulting Dev.

    2018/12/5 %FFQ3BDFS%FFQ %JWF re:Growth 2018

  2. ࣗݾ঺հ  • ιϦϡʔγϣϯΞʔΩςΫτ • ೥݄ೖࣾ —೥ؒ4*FSͰ"1ΤϯδχΞ • ࠷ۙ͞Θ͍ͬͯΔαʔϏε —&,4

    4VNFSJBO ৓؛௚رʢδϣ΢ΨϯφΦΩʣ "84ࣄۀຊ෦ίϯαϧςΟϯά෦

  3. re:Invent 2018 KeyNote 

  4. ࠓ೔࿩͢͜ͱ  w%FFQ3BDFSͰԿ͕Ͱ͖Δͷ͔ɹʙNJO w%FFQ3BDFSΛͲ͏΍ͬͯಈ͔͢ͷ͔ɹʙNJO w%FFQ3BDFS͸Ͳ͏΍ֶͬͯΜͰ͍Δͷ͔ɹʙNJO

  5. %FFQ3BDFSͰԿ͕Ͱ͖Δͷʁ 5

  6. %FFQ3BDFSͰԿ͕Ͱ͖Δͷʁ  ڧԽֶशΛֶ΂Δ

  7. %FFQ3BDFS஀ੜͷഎܠ  How can we put Reinforcement Learning in the

    hands of all developers?

  8. %FFQ3BDFS͸ڧԽֶशΛֶͿͨΊͷखஈ  wڧԽֶशΛ։ൃऀͷखʹ౉͢ ΤΩαΠςΟϯάͳखஈ wڧԽֶशͷϋϯζΦϯΛఏڙ

  9.  ڧԽֶशͱ͸ʁ

  10. ػցֶशͷछྨ  UCL Course on RL Lecture 1: ntroduction to

    Reinforcement Learning wڭࢣ͋Γֶश wڭࢣͳֶ͠श wڧԽֶशʢ%FFQ3BDFSʣ

  11. ࣗಈӡస 

  12. ғޟকع 

  13.  ڧԽֶशͬͯͲ͏΍Δͷʁ

  14. ڧԽֶशʢྫʣ  ใु RLΞϧΰϦζϜ wΤαΛͨ͘͞Μ৯΂ͯ wఢ͕͍ͳ͍ͱ͜ΖʹਐΜͰ wγϛϡϨʔγϣϯ wใुΛ࠷େԽ

  15. %FFQ3BDFSΛಈ͔ͯ͠ΈΔ 15

  16. %FFQ3BDFSΛಈ͔͢·Ͱ  wεςοϓ̍ɿ3FXBSEؔ਺࡞੒ wεςοϓ̎ɿγϛϡϨʔγϣϯ wεςοϓ̏ɿ෺ཧͰ૸ΒͤΔ

  17. %FFQ3BDFSΛಈ͔͢·Ͱ  wεςοϓ̍ɿ3FXBSEؔ਺࡞੒ wεςοϓ̎ɿγϛϡϨʔγϣϯ wεςοϓ̏ɿ෺ཧͰ૸ΒͤΔ

  18. εςοϓ̍ɿ3FXBSEؔ਺  ใुؔ਺ʢPythonʣ ɾEJTUBODF@GSPN@DFOUFS ɹηϯλʔϥΠϯ͔Βͷڑ཭ ɾPO@USBDL ɹं྆ͷલ෦͕നઢͷ֎ଆʹ͋Δ͔Ͳ͏͔ ɾUISPUUMF ɹंͷ଎౓ɹ͸ఀࢭΛࣔ͠ɺ͸࠷ߴ଎౓ ɾUSBDL@XJEUI

    ɹτϥοΫ෯ ɹ ɹͳͲͳͲ Πϯϓοτ Ξ΢τϓοτ

  19. εςοϓ̍ɿ3FXBSEؔ਺  NBSLFS@ USBDL@XJEUI NBSLFS@ USBDL@XJEUI NBSLFS@ USBDL@XJEUI SFXBSEF JGEJTUBODF@GSPN@DFOUFSBOEEJTUBODF@GSPN@DFOUFSNBSLFS@

    SFXBSE FMJGEJTUBODF@GSPN@DFOUFSNBSLFS@ SFXBSE FMJGEJTUBODF@GSPN@DFOUFSNBSLFS@ SFXBSE FMTF SFXBSEFMJLFMZDSBTIFEDMPTFUPPGGUSBDL

  20. %FFQ3BDFSΛಈ͔͢·Ͱ  wεςοϓ̍ɿ3FXBSEؔ਺࡞੒ wεςοϓ̎ɿγϛϡϨʔγϣϯ wεςοϓ̏ɿ෺ཧͰ૸ΒͤΔ

  21. εςοϓ̎ɿϞσϧ࡞੒ 

  22. εςοϓ̎ɿϞσϧ࡞੒ 

  23. %FFQ3BDFSΛಈ͔͢·Ͱ  wεςοϓ̍ɿ3FXBSEؔ਺࡞੒ wεςοϓ̎ɿγϛϡϨʔγϣϯ wεςοϓ̏ɿ෺ཧͰ૸ΒͤΔ

  24. εςοϓ̏ɿ෺ཧͰ૸ΒͤΔ  ֶशϞσϧ

  25. εςοϓ̏ɿ෺ཧͰ૸ΒͤΔ 

  26. "84্ͷΞʔΩςΫνϟ  SageMaker RoboMaker S3 kinesis video streams CloudWatch Logs

    Client

  27. %FFQ3BDFS͸Ͳ͏΍ֶͬͯΜͰ͍Δͷ͔ 27

  28. τϨʔχϯά͸ͲͷΑ͏ʹͯ͠ߦΘΕΔ͔ʁ  https://www.slideshare.net/AmazonWebServices/robocar-rally-2018-aim206r20-aws-reinvent-2018 ɾ45"5&ɿঢ়ଶ ɹ%FFQ3BDFSͷϑϩϯτΧϝϥ ɾ3&8"3%ɿใु ɹηϯλʔϥΠϯʹ͚ۙΕ͹(PPE ɹεϐʔυ͕ग़͍ͯΕ͹(PPE ɾ"$5*0/ɿߦಈ ɹεϐʔυΛ্͛Δ

    ɹӈʹۂ͕Δɺࠨʹۂ͕Δ

  29. τϨʔχϯά͸ͲͷΑ͏ʹͯ͠ߦΘΕΔ͔ʁ  "$5*0/ ɾεϐʔυΛ্͛Δ ɾ௚ਐ͢Δ ɾӈʹۂ͕Δ ɾࠨʹۂ͕Δ t=0 S0

  30. τϨʔχϯά͸ͲͷΑ͏ʹͯ͠ߦΘΕΔ͔ʁ  "$5*0/ ɾεϐʔυΛ্͛Δ ɾ௚ਐ͢Δ ɾӈʹۂ͕Δ ɾࠨʹۂ͕Δ t=0 S0

  31. τϨʔχϯά͸ͲͷΑ͏ʹͯ͠ߦΘΕΔ͔ʁ  t=1 S "$5*0/ ɾεϐʔυΛ্͛Δ ɾ௚ਐ͢Δ ɾӈʹۂ͕Δ ɾࠨʹۂ͕Δ 1

  32. τϨʔχϯά͸ͲͷΑ͏ʹͯ͠ߦΘΕΔ͔ʁ  t=1 S "$5*0/ ɾεϐʔυΛ্͛Δ ɾ௚ਐ͢Δ ɾӈʹۂ͕Δ ɾࠨʹۂ͕Δ R

    :ಓ֎ΕͨͷͰใुͳ͠ 1

  33. τϨʔχϯά͸ͲͷΑ͏ʹͯ͠ߦΘΕΔ͔ʁ  "$5*0/ ɾεϐʔυΛ্͛Δ ɾ௚ਐ͢Δ ɾӈʹۂ͕Δ ɾࠨʹۂ͕Δ t=0 S0

  34. τϨʔχϯά͸ͲͷΑ͏ʹͯ͠ߦΘΕΔ͔ʁ  "$5*0/ ɾεϐʔυΛ্͛Δ ɾ௚ਐ͢Δ ɾӈʹۂ͕Δ ɾࠨʹۂ͕Δ t=0 S0

  35. τϨʔχϯά͸ͲͷΑ͏ʹͯ͠ߦΘΕΔ͔ʁ  t=1 S "$5*0/ ɾεϐʔυΛ্͛Δ ɾ௚ਐ͢Δ ɾӈʹۂ͕Δ ɾࠨʹۂ͕Δ 1

  36. τϨʔχϯά͸ͲͷΑ͏ʹͯ͠ߦΘΕΔ͔ʁ  t=1 S "$5*0/ ɾεϐʔυΛ্͛Δ ɾ௚ਐ͢Δ ɾӈʹۂ͕Δ ɾࠨʹۂ͕Δ R

    :ঢ়گʹԠͨ͡ใु 1

  37. τϨʔχϯά͸ͲͷΑ͏ʹͯ͠ߦΘΕΔ͔ʁ  https://www.slideshare.net/AmazonWebServices/robocar-rally-2018-aim206r20-aws-reinvent-2018

  38. ·ͱΊ 38

  39. ·ͱΊ  w%FFQ3BDFS͸ڧԽֶशΛֶͿͨΊͷखஈ w%FFQ3BDFS͸ڧԽֶशͱ͔ؔ܎ͳ͘୯७ʹָ͍͠ wϨʔεେձ΋͋ΔͷͰΈΜͳࢀՃ͠Α͏ʂʂΞϝϦΧͰʁ

  40. 40 ԶͰڧԽֶशΛ ֶΜͰ͘Εʂʂ ࠓͳΒˈ249

  41.  Let's start reinforcement learning with DeepRacer

  42. 42