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
DeepRacer for learning RL
Search
貞松政史
April 06, 2019
Technology
0
1.2k
DeepRacer for learning RL
2019.4.6 Developers.IO at OKAYAMA.
貞松政史
April 06, 2019
Tweet
Share
More Decks by 貞松政史
See All by 貞松政史
予知保全利用を目指した外観検査AIの開発 〜画像処理AIを用いた外観画像に対する異常検知〜
sadynitro
0
210
20230904_GoogleCloudNext23_Recap_AI_ML
sadynitro
0
630
Foundation Model全盛時代を生きるAI/MLエンジニアの生存戦略
sadynitro
0
740
Amazon SageMakerが存在しない世界線 のAWS上で実現する機械学習基盤
sadynitro
0
120
Amazon SageMakerが存在しない世界線のAWS上で実現する機械学習基盤
sadynitro
0
1.3k
みんな大好き強化学習
sadynitro
0
890
機械学習エンジニアはMLOpsの夢を見るか?
sadynitro
0
1.1k
AWSのAIサービスインテグレーション - AIの仕組みを活用した課題解決
sadynitro
0
930
実践Amazon SageMaker - 全体像からユースケースまで
sadynitro
0
2.3k
Other Decks in Technology
See All in Technology
モノリスから小さなシステムへ / Chatworkシステム移行の現在地と今後について@開発生産性カンファレンス
tanakayuki
1
2.5k
Cloud Nativeを支える要素技術・プロダクト・プラクティスの歩み / infrastudy-returns-01-amsy810
masayaaoyama
3
400
マルチエージェントで性能が上がったText-to-SQLのいま/Text-to-SQL
yoshidashingo
2
1.5k
Lernen durch Schmerzen! Mit Reinforcement Learning selbstlernende Systeme entwickeln
joergneumann
0
220
Oracle Modern Data Platform Reference Architecture (MySQL HeatWave Lakehouse編)
oracle4engineer
PRO
2
290
Small_Start_Conscious_Development_Productivity_Improvement_Practices_at_freee
hikarumiyazawa
2
2.1k
TiDBは銀の弾丸になるのか? ~ レバテックの課題と新たな挑戦 ~ TiDB User Day 2024
leveragestech
0
350
プロダクト拡大フェーズでプロダクト検証サイクル効率化を目指す過程で見えたもの / Streamlining Product Validation in Growth Phase
kakehashi
5
5.6k
Oracle Exadata Database Service:サービス概要のご紹介
oracle4engineer
PRO
0
8k
【Oracle GoldenGate 最新情報&テクニカルセミナー】[Session01] Oracle GoldenGate 最新情報&最新事例
oracle4engineer
PRO
2
150
Oracle Base Database Service:サービス概要のご紹介
oracle4engineer
PRO
0
11k
作りすぎない技術 - API時代の開発努力の在り方について考える / Thinking about the state of development efforts in the API era
yokawasa
10
7.1k
Featured
See All Featured
Robots, Beer and Maslow
schacon
PRO
155
8k
Adopting Sorbet at Scale
ufuk
69
8.8k
Building Adaptive Systems
keathley
33
2k
Thoughts on Productivity
jonyablonski
62
4k
Code Reviewing Like a Champion
maltzj
516
39k
The Cult of Friendly URLs
andyhume
74
5.8k
Side Projects
sachag
451
41k
Designing Experiences People Love
moore
136
23k
It's Worth the Effort
3n
180
27k
Helping Users Find Their Own Way: Creating Modern Search Experiences
danielanewman
24
2k
Visualizing Your Data: Incorporating Mongo into Loggly Infrastructure
mongodb
34
9k
Imperfection Machines: The Place of Print at Facebook
scottboms
261
12k
Transcript
4 D 29 26 1 . 0 I 1
& .-* (2 ,0'/4"# 51 83;7 +)
!&%$9( 6: Attention
3 #cmdevio2019
4 os t m ( L @S g E b
i _d L rMI D @ E ( ( ( ) ( e a n k AWS E
5 DeepRacer
6 D
7 ) (
8 …
9 DeepRacer 4 D 26 9 01 .
10 DeepRacer A A A
11
1 2 3
12 DeepRacer
13
14 DeepRacer 1/18
3D AWS DeepRacer League
15 DeepRacer https://aws.amazon.com/jp/deepracer/
16 DeepRacer ! &%$ +)*2 1 '/*2
(#-, 0. "
17 3D AWS RoboMaker Robot Operating System (ROS) Gazebo rqt
18 AWS DeepRacer League ⁻ 0 1 : 9 A
⁻ 9 2 R ⁻ ⁻ D I ⁻ 1 2 ⁻ https://aws.amazon.com/jp/deepracer/league/
19
20 (Artificial Intelligence, AI) (Machine Learning, ML)
NeuralNetwork DeepLearning
21
22 = 1 (
) ( (
23 L N - ) ( - D Q
24 DeepRacer Cliped PPO PPO (Proximal
Policy Optimization) OpenAI2017
25 ( ( )
)
26 1
27 ) () (
28 DeepRacer
29 DeepRacer + + +
30 DeepRacer
31 DeepRacer …
32 DeepRacer
33 orz
34 DeepRacer + + +
35 DeepRacer D A D
36 $ ' + (# &!
%"
37 ( ) ) https://docs.aws.amazon.com/ja_jp /deepracer/latest/developerguide/ deepracer-train-models-define- reward-function.html
38
39 ⁻ 10 ⁻
:
40 SageMaker RL + RoboMaker
41 SageMeker RLRoboMakerGA
42 SageMaker “RL” ⁻ ⁻ M ⁻ M M
⁻ M ⁻ ⁻ ⁻ J M S
43 DeepRacer ) D ( ) ) ( )
44 SageMaker
https://dev.classmethod.jp/machine -learning/sagemaker-robomaker- deepracer-sample/
45 $# "
! https://github.com/awslabs/amazon-sagemaker-examples
46 Jupyter !
47 ( ( )
48
49 2 1
50 2 2
51 (. ( )(
52 $2# " /1(+ $2#,- ! https://docs.aws.amazon.com/ja_jp/deepracer/latest/developerguide/deepracer -iteratively-enhance-reward-functions.html *
$2%) '.0& )
53 Best Practices when training with PPO
(Unity Technologies) https://github.com/Unity-Technologies/ml-agents/blob/master/docs/Training-PPO.md
54 DeepRacer "% ! "%
$# ! !
55 DeepRacer
56 DeepRacer
57 DeepRacer
58 DeepRacer
59 DeepRacer
60
61 • g • + + • M D c
• R S D a k • b • LL e
62 DeepRacer
None