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
今日のハイライトをシステマティックに
sadynitro
1
35
はじめてのレコメンド〜Amazon Personalizeを使った推薦システム超超超入門〜
sadynitro
0
670
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
470
20230904_GoogleCloudNext23_Recap_AI_ML
sadynitro
0
680
Foundation Model全盛時代を生きるAI/MLエンジニアの生存戦略
sadynitro
0
790
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
150
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
1.5k
みんな大好き強化学習
sadynitro
0
950
機械学習エンジニアはMLOpsの夢を見るか?
sadynitro
0
1.2k
Other Decks in Technology
See All in Technology
チームを主語にしてみる / Making "Team" the Subject
ar_tama
4
300
APIテスト自動化の勘所
yokawasa
7
4.1k
バクラクにおける可観測性向上の取り組み
yuu26
3
400
pandasはPolarsに性能面で追いつき追い越せるのか
vaaaaanquish
4
4.3k
Amazon FSx for NetApp ONTAPを利用するにあたっての要件整理と設計のポイント
non97
1
160
オニオンアーキテクチャで実現した 本質課題を解決する インフラ移行の実例
hryushm
14
3k
プロダクトエンジニアが活躍する環境を作りたくて 事業責任者になった話 ~プロダクトエンジニアの行き着く先~
gimupop
1
460
GitHub Universe: Evaluating RAG apps in GitHub Actions
pamelafox
0
170
omakaseしないための.rubocop.yml のつくりかた / How to Build Your .rubocop.yml to Avoid Omakase #kaigionrails
linkers_tech
3
710
オーティファイ会社紹介資料 / Autify Company Deck
autifyhq
9
120k
Figma Dev Modeで進化するデザインとエンジニアリングの協働 / figma-with-engineering
cyberagentdevelopers
PRO
1
430
ABEMA のコンテンツ制作を最適化!生成 AI x クラウド映像編集システム / abema-ai-editor
cyberagentdevelopers
PRO
1
180
Featured
See All Featured
Adopting Sorbet at Scale
ufuk
73
9k
JavaScript: Past, Present, and Future - NDC Porto 2020
reverentgeek
47
5k
ReactJS: Keep Simple. Everything can be a component!
pedronauck
664
120k
Fantastic passwords and where to find them - at NoRuKo
philnash
50
2.8k
The Cult of Friendly URLs
andyhume
78
6k
The Art of Programming - Codeland 2020
erikaheidi
51
13k
Fireside Chat
paigeccino
32
3k
jQuery: Nuts, Bolts and Bling
dougneiner
61
7.5k
A Tale of Four Properties
chriscoyier
156
23k
For a Future-Friendly Web
brad_frost
175
9.4k
What's new in Ruby 2.0
geeforr
342
31k
10 Git Anti Patterns You Should be Aware of
lemiorhan
654
59k
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