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

원석이의 모두연에서 강화학습 보석되기

Avatar for Wonseok Jung Wonseok Jung
December 15, 2018
0
410

원석이의 모두연에서 강화학습 보석되기

Avatar for Wonseok Jung

Wonseok Jung

December 15, 2018
Tweet

More Decks by Wonseok Jung

See All by Wonseok Jung
Ai for business -self car driving
Avatar for Wonseok Jung wonseokjung
0
190
reinforcement_learning_.pdf
Avatar for Wonseok Jung wonseokjung
2
1.5k
NeuralIPS
Avatar for Wonseok Jung wonseokjung
0
400
Introduction Deep Reinforcement Learning
Avatar for Wonseok Jung wonseokjung
0
150
Deep reinforcemenet learning -2
Avatar for Wonseok Jung wonseokjung
0
190
Deep Reinforcement Learning - Introduction
Avatar for Wonseok Jung wonseokjung
1
630
How to become a datascientist ?
Avatar for Wonseok Jung wonseokjung
2
2.3k
Review of Taylor series
Avatar for Wonseok Jung wonseokjung
1
120
꿈꾸는 Agent
Avatar for Wonseok Jung wonseokjung
2
140

Featured

See All Featured
Build The Right Thing And Hit Your Dates
Avatar for Maggie C. maggiecrowley
36
2.8k
Building Adaptive Systems
Avatar for Chris Keathley keathley
43
2.6k
Principles of Awesome APIs and How to Build Them.
Avatar for Keavy McMinn keavy
126
17k
The Art of Programming - Codeland 2020
Avatar for Erika Heidi erikaheidi
54
13k
What's in a price? How to price your products and services
Avatar for Michael Herold michaelherold
246
12k
The Psychology of Web Performance [Beyond Tellerrand 2023]
Avatar for Tammy Everts tammyeverts
48
2.8k
Templates, Plugins, & Blocks: Oh My! Creating the theme that thinks of everything
Avatar for Michelle Schulp Hunt marktimemedia
31
2.4k
Building Better People: How to give real-time feedback that sticks.
Avatar for Will Jessup wjessup
367
19k
Measuring & Analyzing Core Web Vitals
Avatar for Philip Tellis bluesmoon
7
490
Raft: Consensus for Rubyists
Avatar for Patrick Van Stee vanstee
140
7k
Easily Structure & Communicate Ideas using Wireframe
Avatar for Afnizar Nur Ghifari afnizarnur
194
16k
Git: the NoSQL Database
Avatar for Brandon Keepers bkeepers
PRO
430
65k

Transcript

  1. ਗࢳ੉੄ݽفোীࢲъച೟णࠁࢳغӝ 8POTFPL+VOH

  2. Modulabs CTRL ە੢

  3. Modulabs CTRL ە੢ ъച೟णোҳ߂ъച೟ण؀ഥ

  4. Modulabs CTRL ە੢ Modulabs RLXDL ە੢ ъച೟णোҳ߂ъച೟ण؀ഥ

  5. Modulabs CTRL ە੢ Modulabs RLXDL ە੢ %FFQ3FJOGPSDFNFOU-FBSOJOHझఠ٣ ъച೟णোҳ߂ъച೟ण؀ഥ

  6. Modulabs CTRL ە੢ Modulabs RLXDL ە੢ Modulabs KAIR ҕزە੢ %FFQ3FJOGPSDFNFOU-FBSOJOHझఠ٣

    ъച೟णোҳ߂ъച೟ण؀ഥ

  7. Modulabs CTRL ە੢ Modulabs RLXDL ە੢ Modulabs KAIR ҕزە੢ %FFQ3FJOGPSDFNFOU-FBSOJOHझఠ٣

    ъച೟णোҳ߂ъച೟ण؀ഥ 3FJOGPSDFNFOUMFBSOJOHਵ۽3PCPUJDT೟ण

  8. Modulabs CTRL ە੢ Modulabs RLXDL ە੢ Modulabs KAIR ҕزە੢ Modulabs

    ಽ੖झ௥ 3FJOGPSDFNFOUMFBSOJOHਵ۽3PCPUJDT೟ण %FFQ3FJOGPSDFNFOU-FBSOJOHझఠ٣ ъച೟णোҳ߂ъച೟ण؀ഥ

  9. Modulabs CTRL ە੢ Modulabs RLXDL ە੢ Modulabs KAIR ҕزە੢ Modulabs

    ಽ੖झ௥ 3FJOGPSDFNFOUMFBSOJOHਵ۽3PCPUJDT೟ण _ӝಽ੖झ௥ীࢲҕࠗ઺  ӝъച೟णӝୡबചಌप੉  ੉ߣীࣻܐޅೡ٠ %FFQ3FJOGPSDFNFOU-FBSOJOHझఠ٣ ъച೟णোҳ߂ъച೟ण؀ഥ

  10. Modulabs CTRL ە੢ Modulabs RLXDL ە੢ Modulabs KAIR ҕزە੢ Modulabs

    ಽ੖झ௥ 3FJOGPSDFNFOUMFBSOJOHਵ۽3PCPUJDT೟ण _ӝಽ੖झ௥ীࢲҕࠗ઺  ӝъച೟णӝୡबചಌप੉  ੉ߣীࣻܐޅೡ٠ %FFQ3FJOGPSDFNFOU-FBSOJOHझఠ٣ ъച೟णোҳ߂ъച೟ण؀ഥ Modulabs DeepLearningCollege ъച೟णোҳਗ ֙ъച೟ण೐۽ં౟ ֤ࣗޙ੘ࢿѐ৮ܐ ѐোҳ૓೯઺ ࣗ੢שҗ ઑӝࣻܐೣ

  11. _

  12. "XBSET  Ӗ۽ߥ҃ઁޙചߊ੹؀࢚ "*ӝࣿഄनࠗޙ؀࢚࢚ࣻ Ҵഥ੄ਗ੢಴ହ੢ࣻৈ 
 .PEVMBCT'JSTUDMBTTJGJDBUJPODPNQFUJUJPOT SE
 .PEVMBCT'JSTU3-$PNQFUJUJPOT
 TU


    
 .PEVMBCT4FDPOE3-$PNQFUJUJPOT TU 0QFO"*3FJOGPSDFNFOUMFBSOJOH3FUSP 5PQ ѐ੄"XBSETࣻৈ
 


  13. 
 1SFTFOUBUJPOBOE-FDUVSFT ਘ_ 5FOTPSGMPX,33FJOGPSDFNFOU-FBSOJOH ऱ੉Ӓېݠ%*:ъച೟ण ա݅੄गಌܻ݃য়ڣٯڣٯٜ݅ӝ  IUUQTXXXZPVUVCFDPNXBUDI W#.*JSCW2X 

    ী੉੹౟ܳࠗఌ೧5IFSJTFPG3FJOGPSDFNFOU-FBSOJOH IUUQTXXXZPVUVCFDPNXBUDI WVI9V"L3G.2 TUೣԋೞח٩۞׬ஶಌ۠झ3VOOJOH"* IUUQTXXXTMJEFTIBSFOFUXPOTFPLKVOHEFFQMFBSOJOHDPOG ౵੉௑௏ܻইੋҕ૑מगಌܻ݃য়੄Ѣ੄ݽٚѪ IUUQTTQFBLFSEFDLDPNXPOTFPLKVOHBEPUJTVQFSNBSJP XJUISFJOGPSDFNFOUMFBSOJOH  ೠҴ੿ࠁ୊ܻ೟ഥъച೟ण੉ۿҗपઁ IUUQTXXXTMJEFTIBSFOFUXPOTFPLKVOHSM ా҅աۄъച೟ण੉ۿҗपઁ IUUQTXXXTMJEFTIBSFOFUXPOTFPLKVOHSM ੗അҊ١೟Ү&YQMPSBUJPO .FUB3-ӒܻҊա
 IUUQTXXXTMJEFTIBSFOFUXPOTFPLKVOHSM ؘ੉ఠঠ֥੗যࢲ৬_ؘ੉ఠࢎ੉঱झח୊਺੉૑  IUUQTTQFBLFSEFDLDPNXPOTFPLKVOHIPXUPCFDPNFB EBUBTDJFOUJTU ѐ੄ߊ಴߂ъ੄
 ো݈ѐߊ಴৘੿


  14. 3FTFBSDI <>8POTFPL +VOH 3&8"3%4)"1*/(*4"--:06/&&%
 -FBSOJOHTLJMMTXJUIBTQFDJGJFESFXBSEGVODUJPO 1PTU"*   <>8POTFPLKVOH .JOKJ,JN

    4FPLKFPOH4POH.PEVMBCT 1PTU"*  &YQMPSBUJPONFUIPEGPSSFEVDJOHVODFSUBJOUZVTJOH2FOUSPQZJOEFFQ SFJOGPSDFNFOUMFBSOJOH #FTU1PTUFS"XBSE  + ࣗ੢שҗೣԋೞחૌѢ਍োҳs ѐ੄֤ޙ੘ࢿ


  15. &5$ ѐ੄୹౸ࢎীࢲъച೟णҙ۲୹౸ઁ੄ ѐ੄#MPH੘ࢿ ѐ੄ਬై࠳ز৔࢚স۽٘
 ֙ѐਘрझ݃౟ಂషܻ೐۽ં౟૓೯

  16. ੌ ҕࠗ ӝఋ١١

  17. ъച೟णҙ੼ীࢲ࠙ࢳ
 ੉ۧѱ൨ٚੌਸ৵ যڌѱ೮ਸө  റഥبহח֙

  18. 5PEBZ  8IBUJT3FJOGPSDFNFOU-FBSOJOH   ݽفোਸ݅աӝ੹ө૑  ݽفোਸ݅աҊٍ  ъച೟णҙ੼ীࢲ࠙ࢳ

  19. 'JSTU 8IBUJT3FJOGPSDFNFOU-FBSOJOH

  20. LAW OF EFFECT - &EXBSE5IPSOEJLF   - -BXPGFGGFDUযڃ೯ز੄Ѿҗо݅઒झ۞਋ݶ׮਺ীبӒ೯زਸ߈ࠂೠ׮ ߈؀۽݅઒ೞ૑ঋਵݶӒ೯زਸೞ૑ঋח׮

    - 3FJOGPSDFNFOU ъച ੉੹ীੌযդ೯زਸ߈ࠂೞѱ݅٘ח੗ӓ - 1VOJTINFOU ୊ߥ ੉੹ীੌযդ೯زਸೖೞѱ݅٘ח੗ӓ HOW ANIMALS LEARN

  21. EXAMPLE OF THE LAW OF EFFECT HOW ANIMALS LEARN

  22. INTERACTION WITH ENVIRONMENT &OWJSPONFOU &YQFSJFODF -FBSO *OUFSBDUJPO HOW HUMANS LEARN

  23. HOW HUMANS LEARN? - 3FJOGPSDFNFOU੉੹ীੌযդ೯زਸ߈ࠂೞѱ݅٘ח੗ӓ - 1VOJTINFOU੉੹ীੌযդ೯زਸೖೞѱ݅٘ח੗ӓ HOW HUMANS LEARN

  24. HOW HUMANS LEARN -TAP BALL %BZ %BZ %BZ %BZ ୭Ҋ੼ࣻ


    ݏ਷പࣻ ୭Ҋ੼ࣻ
 ݏ਷പࣻ ୭Ҋ੼ࣻ
 ݏ਷പࣻ ୭Ҋ੼ࣻ ݏ਷പࣻ HOW HUMANS LEARN

  25. TAP BALL DAY 5 %BZ ୭Ҋ੼ࣻ ݏ਷പࣻ HOW HUMANS LEARN

  26. SIMILAR LEARNING METHODS B/W ANIMALS AND HUMANS HOW HUMANS LEARN

    1VOJTINFOU 1VOJTINFOU 1VOJTINFOU

  27. REINFORCEMENT LEARNING &OWJSPONFOU &YQFSJFODF -FBSO REINFORCEMENT LEARNING *OUFSBDUJPO "(&/5

  28. LEARNING 3FJOGPSDFNFOUMFBSOJOH਷3FXBSE ࠁ࢚ ਸ୭؀ചೞחBDUJPO ೯ز ਸࢶఖೠ׮ -FBSOFS ߓ਋ח੗ חৈ۞BDUJPOਸ೧ࠁݴ SFXBSEܳо੢֫ѱ߉חBDUJPOਸ଺ח׮

    ࢶఖػBDUJPO੉׼੢੄SFXBSEࡺ݅ইצ ׮਺੄࢚ടژח׮਺ੌযաѱؼ SFXBSEীب৔ೱਸՙசࣻب੓׮ "DUJPO ׼੢੄ ࢚ട߸ച ޷ې੄࢚ട 3FXBSE ޷ې੄3FXBSE REINFORCEMENT LEARNING

  29. MARKOV DECISION PROCESS "DUJPO "HFOU &OWJSPONFOU 3FXBSE At Rt 4UBUF

    St Rt+1 St+1 REINFORCEMENT LEARNING

  30. STATE-ACTION VALUE FUNCTION 4UBUF"DUJPOWBMVF REINFORCEMENT LEARNING

  31. OPTIMAL POLICY REINFORCEMENT LEARNING 0QUJNBM4UBUF"DUJPOWBMVFGVODUJPO

  32. Agent Exploitation Exploration ? EXPLOITATION AND EXPLORATION REINFORCEMENT LEARNING

  33. IMPORTANCE OF EXPLORATION ࣄ੉ 3VTTJBO#MVF ࢓ $VSJPTJUZ
 ಽ੉ .VODILJO ࢓

    'PPE REINFORCEMENT LEARNING

  34. IMPORTANCE OF EXPLORATION-2 REINFORCEMENT LEARNING ಽ੉ ࣄ੉ ;FSP
 FYQMPSBUJPO &YQMPSBUJPO

  35. IMPORTANCE OF EXPLORATION-3 REINFORCEMENT LEARNING ಽ੉ ࣄ੉ 'BJM

  36. MARKOV DECISION PROCESS &OWJSPONFOU 3FXBSE At Rt St Rt+1 St+1

    REINFORCEMENT LEARNING 5BQUIFCBMM 1PTJUJWF3FXBSE


  37. ݽفো
 ੹74റ

  38. ݽفোਸ݅աӝө૑
 _

  39. $BMJGPSOJB ೞܖझா઴ 
 ࢲೝইஜߏ਍ز೟Үࣻসҕࠗ੷֘ߏ਍زਫ਼

  40. .PWJOHUP/: ׏਄ਵ۽؀೟Үಞੑ
 ੗زର۽ுܻನפইীࢲ׏਄ө૑਍੹
 ӝ۾੸ੋ಩ࢸ

  41. /FX:PSL ੌزউदр੗Ҋ਍੹ೞৈ׏਄ীب଱ƕƕ
 ுܻನפই৬ցޖ׮ܲജ҃ী׼ട
 ࢎۈٜ಴੿
 Ѧ਺ࣘب
 بࢲҙীࢲࢎח೟ࢤٜ
 ҃੬ 


  42.  ցޖցޖয۰਍ઔস  ৈ۞աۄীࢲৡ೟ࢤٜҗ஖ৌೠ҃੬  ઔসٸө૑ೞܖઙੌҕࠗ ҕࠗ ҕࠗ  ݈ೞחदр੉ইөਕࢲࢎۈٜҗ੄ࣗాରױ

     ੉যಪ ݽ੗ റ٘ ݃झ௼଱ਊೞҊ׮ש  ݫन੷ө૑ରױ


  43.  ೠҴਵ۽ӈҴ  ࣻ૒ҳઑ૒੢ޙച҃೷  ҙबী؀ೠف۰਑  ׮द޷Ҵਵ۽جইоӝ۽҅ദ

  44.  ޷Ҵਵ۽جইоӝ੹
 ോधӝрীݽف੄োҳࣗীଵৈ  ݽفোীࢲҕࠗೞחৌ੿੸ੋࢎۈٜҗ੄݅թ  ೣԋࢿ੢ೞҊरযೠҴীࢲ֙؊թӝ۽Ѿ੿

  45. ݽفোਸ݅աҊդറ
 _13&4&/5

  46. ࢎۈ

  47. োҳਗ ഥࢎਗ ೟ࠗࢤ ؀೟ਗࢤ ߔࣻ ઱ࠗ Ҋ١೟ࢤ Үࣻ ѐߊ੗ ࣻ೟੗

    ׮নೠ୹न੄ݽفোোҳਗٜ

  48. োҳਗ ഥࢎਗ ೟ࠗࢤ ؀೟ਗࢤ ߔࣻ ઱ࠗ Ҋ١೟ࢤ Үࣻ ѐߊ੗ ࣻ೟੗

    ׮নೠ୹न੄ݽفোোҳਗٜ Үਭ

  49. োҳਗ ഥࢎਗ ೟ࠗࢤ ؀೟ਗࢤ ߔࣻ ઱ࠗ Ҋ١೟ࢤ Үࣻ ѐߊ੗ ࣻ೟੗

    ׮নೠ୹न੄ݽفোোҳਗٜ Үਭ ࣻ೟ ஹೊఠҗ೟ ٩۞׬ ъച೟ण ࠶۾୓ੋ

  50. োҳਗ ഥࢎਗ ೟ࠗࢤ ؀೟ਗࢤ ߔࣻ ઱ࠗ Ҋ١೟ࢤ Үࣻ ѐߊ੗ ࣻ೟੗

    ׮নೠ୹न੄ݽفোোҳਗٜ Үਭ ࣻ೟ ஹೊఠҗ೟ ٩۞׬ ъച೟ण ࠶۾୓ੋ োҳ

  51. োҳਗ ഥࢎਗ ೟ࠗࢤ ؀೟ਗࢤ ߔࣻ ઱ࠗ Ҋ١೟ࢤ Үࣻ ѐߊ੗ ࣻ೟੗

    ׮নೠ୹न੄ݽفোোҳਗٜ Үਭ ࣻ೟ ஹೊఠҗ೟ ٩۞׬ ъച೟ण ࠶۾୓ੋ োҳ ъച೟ण ৔࢚୊ܻ ੗োয୊ܻ ۽ࠁ౮झ ݽ߄ੌݠन۞׬
  52. None
  53. None

  54. ࢿ੢ೡࣻ߆ীহ঻؍ࣁо૑  ׮ܲѪ੉૑ౣܽѪ੉ইפ׮ ఋੋ੄ҙ੼ীࢲࢤп   $PNNVOJDBUJPO ੄ࢎࣗా షۿ ߊ಴

      %FFQMFBSOJOH 3FJOGPSDFNFOU-FBSOJOH ౠ੿࠙ঠ૑ध

  55. )BQQJOFTTJODSFBTFQSPEVDUJWF  ച੢ಿҕ੢झ݃౟ಂషܻ۽੄੹ജ  রӏݽ੄֙ѐਘ೐۽ં౟ীଵৈ  ݾ಴୷੸ػؘ੉ఠܳ੉ਊೞৈझ݃౟ಂషܻীࢲੌೞח
 ੘স੗ٜ੉೯ࠂೞѱੌೡࣻ੓ѱ  ݅઒х࢚थࢤ࢑۝࢚थ

  56. Relation Analysis ࢎۈ ӝ҅ ઁಿ दझమ੄ҙ҅ܳ࠙ࢳ

  57. Humans ҕ੢੄੘স੗ٜ੄੿ࠁ౵ঈ ੉ܴ ঴ҷ ա੉ ࢿ߹  ੘স੗ٜҙ଴ ಴੿ ރ૙

    ಁఢ ҃۽ ؀ചղਊ  ੘স੗ٜҗ੄ࣗాदب

  58. $PNNVOJDBUJPO ੘স੗ ӝઓഈ۱স୓ٜҗ੄ഈস੉ݒ਋ݒ਋઺ਃೞ׮ ౠ൤അ੢ীࢲੌೞदחٜ࠙җ੄ࣗా੉ઁੌয۵׮ tয়৔যߓ਋Ҋरਵद׮ҳਃ u

  59. tোରݻੌթওয u tթ਷োରੌࣻח୨ੌੑפ׮ ࢎਊೞदѷणפө u $IBUCPU  $IBUCPUਸాೞৈ੿ࠁܳ঳חѪ੉оמೞ׮  )VNBO)VNBOীࢲয়חࠛ೙ਃೠх੿ࣗݽܳ઴ੌࣻ੓׮

  60. t.442-u t1ZUIPOu t1ZNTTRMu tNFTTBOHFSu GFBUةܻࣻఋߨ tQMBUGPSNu tTNBSUQIPOFu t42-u t-BOHVFHFu %FWFMPQFBDIBUCPU

  61. 0CKFDUEFUFDUJPO ઁಿ੉ѱޤ૑ 0CKFDUEFUFDUJPOઁಿ੉ܴ ࠳ے٘ઑ݀ߨ಴द 0CKFDUEFUFDUJPOਸ਽ਊೞৈt੘স੗о਄উݡҊߓ਋ѱೞӝu

  62. 0CKFDUEFUFDUJPO tઁಿ೟णu t%FFQ-FBSOJOHu :0-07 t-BCFMJOHu t੉ઁಿޤ૑ u tTNBSUQIPOFu

  63. ೐۽ં౟৮ܐ ݽفো੉হ঻׮ݶ੉ܖ૑ޅ೮ਸѢীਃ

  64. ߅కഅ - ־о ഥࢎীࢲ ੋ੿߉חо  ੹ޙ࠙ঠীࢲର߹ചػ৉۝ਸࠁਬೞҊ੓׮  যڃդҙীبध૑ঋחڰѢ਍ৌ੿ਸо૑Ҋ੓׮ 

    ־ҳ৬بೣԋࣗాҗഈসীמೞ׮

  65. ъച೟णҙ੼ীࢲ࠙ࢳ
 ੉ۧѱ൨ٚੌਸ৵ যڌѱ೮ਸө  റഥبহח֙

  66. MARKOV DECISION PROCESS "DUJPO "HFOU &OWJSPONFOU 3FXBSE At Rt 4UBUF

    St Rt+1 St+1 REINFORCEMENT LEARNING

  67. ACTIONS "DUJPO "HFOU &OWJSPONFOU 3FXBSE At Rt 4UBUF St Rt+1

    St+1 REINFORCEMENT LEARNING ਗࢳ

  68. ACTIONS "DUJPO "HFOU &OWJSPONFOU 3FXBSE At Rt 4UBUF St Rt+1

    St+1 REINFORCEMENT LEARNING ਗࢳ

  69. "DUJPO "HFOU &OWJSPONFOU 3FXBSE At Rt 4UBUF St Rt+1 St+1

    REINFORCEMENT LEARNING ਗࢳ ACTIONS

  70. WONSEOK JUNG ߊݺо ݅ചо җ೟੗ Ѥ୷о оࣻ Ѻైӝࢶࣻ ੗زର٣੗੉ց ઁಿ٣੗੉ց

    ੘ҋо EXPLORATION ఋై੉झ౟ ࣿ૘਍৔ ஠ۨ੉ࢲ झ௢ఠ׮੉ߡ ੘о ಁ࣌٣੗੉ց ೾झ౟ۨ੉ց Үਭо ҃৔ஶࢸఢ౟ ؘ੉ఠࢎ੉঱౭झ౟ ੋҕ૑מোҳਗ Үਭо ੋҕ૑מূ૑פয ۽ࠈੋҕ૑מোҳਗ

  71. ೣԋUBTLܳಽযоחૌѢ਑੿न੸ ਭ୓੸൨ٞ 3FXBSE1FOBMUZ

  72. tਗࢳ੉੄ݽفোীࢲъച೟णࠁࢳغӝuੋ૓૞੉ਬ

  73. ਗࢳ ࠁࢳ ݽف੄োҳࣗ ઁо ਗࢳ੉ ࠁࢳ੉غ঻׮חڷ੉ইפ঻णפ׮

  74. ਗࢳ ࠁࢳ োҳਗ ഥࢎਗ ೟ࠗࢤ ؀೟ਗࢤ ߔࣻ ઱ࠗ Ҋ١೟ࢤ Үࣻ

    ѐߊ੗ ࣻ೟੗ ৌ੿੸੉Ҋ ഴܯೠ ݽفোোҳਗשҗೣԋ

  75. ֙ tೠҴীࢲ֙؊թӝ۽Ѿ੿uডࣘਸ૑ఃӝਤ೧޷Ҵਵ۽ਫ਼दجইцפ׮ ъച೟णਵ۽ݽ࣌੉੗োझ۞਍ী੉੹౟೟ण ೟णػݽ؛ਸपޛ SPCPU ਵ۽USBOTGFS ೧৻೟ഥ֤ޙઁ୹ "NB[PO%FFQSBDFS؀ഥଵৈ ਘ 

  76. ֙੷৬ೣԋࠁࢳ੉ؼݽفোо઒ਸࣗѐ೤פ׮

  77. None

  78. Modulabs CTRL

  79. 
 .PEVMBCT$53-3FTFBSDIFS $JUZ6OJWFSTJUZPG/FX:PSL#BSVDI $PMMFHF %BUB4DJFODF.BKPS  $POOFYJPO"*'PVOEFS %FFQ-FBSOJOH$PMMFHF3FJOGPSDFNFOU -FBSOJOH3FTFBSDIFS CTRL

    MEMBERS 8POTFPL+VOH ,ZVOHIXBO,JN 
 .PEVMBCT$53-3FTFBSDIFS )BOTVOH6OJWFSTJUZ
 &MFDUSPOJDJOGPSNBUJPO&OHJOFFSJOH.BKPS  *OUFSFTUFE"* 3FJOGPSFNFOUMFBSOJOH  (BNF )ZP+FPOH+FPO 
 .PEVMBCT$53-3FTFBSDIFS #JOHIBNUPO6OJWFSTJUZ.4PG.FDIBOJDBM &OHJOFFSJOH.BKPS .BUIJOTUSVDUPSBU$PMMFHF1SFQ*OTUJUVUF *OUFSFTU"QQMJDBUJPOPG6OJUZ.-"HFOUT JO3- ("/

  80. CTRL MEMBERS 4FVOH+BF-FF 
 .PEVMBCT$53-3FTFBSDIFS 1SJODFUPO6OJWFSTJUZ$MBTTPG .BUIFNBUJDT.BKPS  4DSBUDIXPSL--$$PGPVOEFS 3FTFBSDI

    &YQFSJNFOUTXJUIUIF.BSLPGG4VSGBDF@ XJUI.BUUIFXEF$PVSDZ*SFMBOEVOEFS )BOZBOH6OJWFSTJUZ
 .4#JPJOGPSNBUJDT #*(-BC 
 6OJUZ%FWFMPQFS .BSWSVT 
 *OUFSFTUFE73"3 
 3FJOGPSDFNFOUMFBSOJOH "*JOUFSBDUJPO 1I% 2VBMJUZ4ZTUFNT-BC1045&$) 
 4FBSDI3FDPNNFOEFS4ZTUFN&OHJOFFS
 *OUFSFTUFE3-"QQMJDBUJPOJO&WFSZXIFSF .PEVMBCT$53-3FTFBSDIFS .PEVMBCT$53-3FTFBSDIFS +XBXPO4FP 7JDT,XPO

  81. CTRL MEMBERS :VOLZV$IPJ 
 .PEVMBCT$53-3FTFBSDIFS 73/&3% 4VIZVL1BSL 
 .PEVMBCT$53-3FTFBSDIFS .BTUFS

    /BUVSBM-BOHVBHF1SPDFTTJOH ,PSFB 6OJWFSTJUZ  %BUB*OHFTUJPO5FBN-FBEFSBU/$40'5 *OUFSFTUFE"QQMZ3FJOGPSDFNFOU-FBSOJOH 5FDIOJRVFTUP%BUB1SPDFTTJOH"SFB ,VSU 
 .PEVMBCT$53-3FTFBSDIFS 3-/&3%
  82. None

  83. Modulabs KAIR

  84. 
 .PEVMBCT,"*33FTFBSDIFS $JUZ6OJWFSTJUZPG/FX:PSL#BSVDI $PMMFHF %BUB4DJFODF.BKPS  $POOFYJPO"*'PVOEFS %FFQ-FBSOJOH$PMMFHF3FJOGPSDFNFOU -FBSOJOH3FTFBSDIFS 3FJOGPSDFNFOU-FBSOJOH

    0CKFDU %FUFDUJPO $IBUCPU KAIR MEMBERS 8POTFPL+VOH $IFPMIVJ.JO 
 .PEVMBCT,"*33FTFBSDIFS #4JO.FDIBOJDBM&OH,PSFB6OJW .4DDBOEJEBUFJO.FDIBOJDBM&OH,PSFB 6OJW 3FTFBSDIGJFME%FFQSFJOGPSDFNFOUMFBSOJOH GPSSPCPUJDT 3PCPUDPOUSPMJOUFSGBDF *OUFSFTUT%FFQ3-BOEPQUJNBMDPOUSPM  3PCPUJDT $IJOFTF 8IJ,XPO 
 .PEVMBCT,"*33FTFBSDIFS JOUFSFTUFE3- NBOJQVMBUPS 4PHBOH6OJW$IFNJDBMBOE#JPFOHJOFFSJOH .FEJQJYFM"*SFTFBSDIFSMFBSOJOHGPS SPCPUJDT 3PCPUDPOUSPMJOUFSGBDF

  85. 
 .PEVMBCT,"*33FTFBSDIFS ,ZVOHIFF6OJWFSTJUZ.FDIBOJDBMBOE 4PGUXBSFFOHJOFFSJOH EVBMNBKPS  *OUFSFTUSPCPUJDTBOETJNVMBUJPO 3- NM BHFOU

    
 .PEVMBCT,"*33FTFBSDIFS 4FPVM/BUJPOBM6OJWFSTJUZ .FDIBOJDBM "FSPTQBDF&OHJOFFSJOH.BKPS  4QBDF/FSE *OUFSFTU3PCPUJDT /BWJHBUJPO$POUSPM  #BUUMFHSPVOE .BDBSPO 
 .PEVMBCT,"*33FTFBSDIFS %BFKFPO6OJWFSTJUZ &MFDUSPOJD*OGPSNBUJPO$PNNVOJDBUJPO &OHJOFFSJOH  *OUFSFTUFE3FJOGPDFNFOU-FBSOJOH  4JN3FBM KAIR MEMBERS 4VCJO:BOH 4FPZFPO:BOH +VOUBF,JN

  86. 
 .PEVMBCT,"*33FTFBSDIFS 4VOHLZVOLXBO6OJW.FDIBOJDBM FOHJOFFSJOH#4 4FPVM/BUJPOBM6OJW.4TUVEFOU *OUFSFTUFE)VNBOPJE 5PSRVFDPOUSPM  3- 


    .PEVMBCT,"*33FTFBSDIFS ,PSFB6OJWFSTJUZ $POUSPM3PCPUJDT 4ZTUFN *OUFSFTU2VBOUJ[FE/FVSBM/FUXPSLTBOE "4*$*NQMFNFOUBUJPO 4UBUFFTUJNBUJPO 3- 
 .PEVMBCT,"*33FTFBSDIFS #4JO$PNQVUFS4DJFODFBOE&OHJOFFSJOH 3FTFBSDI&OHJOFFSBU.FEJQJYFM *OUFSFTUFEJO$POWFY0QUJNJ[BUJPO  $PNQVUFS7JTJPO BOE3FJOGPSDFNFOU -FBSOJOH KAIR MEMBERS %POHIZFPO,JN +FPOHIPPO,JN +JOXPP1BSL

  87. 
 .PEVMBCT,"*33FTFBSDIFS #4JO.BUIFNBUJDTBOE$PNQVUFS 4DJFODFJO,PSFB6OJW .4$PVSTFJO&MFDUSJDBM&OHJO4FPVM /BUJPOBM6OJW 3FTFBSDIGJFME4UPDIBTUJD$POUSPM1SPDFTT KAIR MEMBERS 4JIZVO$IPJ

    4FVOH+BF3ZBO-FF 
 .PEVMBCT,"*33FTFBSDIFS 1SJODFUPO6OJW$MBTTPG .BUIFNBUJDT  FOEUPFOE"*3FTFBSDIFS %FFQ-FBSOJOH;FSP5P"MM4FBTPO1Z5PSDI $POUFOU$POUSJCVUPS *OUFSFTUT%BUBFGGJDJFOU3- $VSJPTJUZESJWFO -FBSOJOH .FUB-FBSOJOH

  88. ਗࢳ ࠁࢳ োҳਗ ഥࢎਗ ೟ࠗࢤ ؀೟ਗࢤ ߔࣻ ઱ࠗ Ҋ١೟ࢤ Үࣻ

    ѐߊ੗ ࣻ೟੗ ֙ೣԋࠁࢳ੉ؼোҳਗݽ૘೤פ׮

  89. ֙ݽفࣻҊ݆ਵ࣑णפ׮ ֙ীب਋ܻೣԋ೧ࠊਃ