SlideShare una empresa de Scribd logo
1 de 83
Descargar para leer sin conexión
強化学習の分散アーキテクチャ変遷
#14
Twitter: @eratostennis
• Include
•
• Gorila, A3C, GA3C, batched A2C, Ape-X, IMPALA
•
• Accelerated Methods for Deep Reinforcement Learning
• Exclude
•
•
• Trace [8]
• Importance Sampling, Tree-backup, Retrace
• UNREAL [9]
•
•
DistBelief[10]
A3C
GA3C
batchedA2C
IMPALA
Gorila
Ape-X
AcceleratedMethods
2012 2015 2016 2017 2018
• Gorila
• A3C
• GA3C
• batched A2C
• Ape-X
• IMPALA
• Accelerated Methods for Deep Reinforcement Learning
Gorila [1]
DQN ( )
Gorila
Results
DQN (6 19 )
DQN 12~14 (6 ) DQN 41/49
A3C [2]
A3C
[3] GA3C
:
•
• on-policy
•
• 1 CPU (GPU )
A3C
• DNN
• CNN2 +FC +Softmax ×2(policy, value)
•
•
•
•
Experiments
LSTM .
•
• Multi-Step
A3C Pong 4
GA3C [3]
GA3C
• A3C CPU/GPU
• DQN, Double-DQN, Dueling Double DQN GPU
• SoTa GPU A3C
• AlphaGO
• 50GPU
• Gorilla DQN 31 100
• GPU
• Queue
•
• TensorFlow
• SoTa
A3C
• 16 , 16CPU
• 4 (Atari ,Brockman)
•
•
•
• GPU
• A3C Replay Memory
Hybrid CPU/GPU A3C (GA3C)
Performance metrics and
trade-offs
•
• CPU-GPU
• GPU
• GPU
• GA3C
• Predictor <=> GPU
• Trainer <=> GPU
• <=>
• Training Per Second (TPS)
•
• Predictions Per Second (PPS)
•
• A3C 5 …
• PPS TPS × 5
Dynamic adjustment of trade-
offs
• TPS
• , DNN ,
•
Atari BOXING Atari PONG
Policy lag in GA3C
• A3C GA3C
•
• k
Maximizing training speed
GPU
: A3C
GPU utilization and DNN size
Large DNN TPS 7% …
GPU ( 12%UP)
: A3C
Effect of TPS on learning
speed
Compares scores
A3C 4 ( ) GA3C 1
Training curves
GA3C LR
Policy lag, learning stability
and convergence speed
•
• TPS
•
• TPS, ,
1~40 …
GA3C
• CPU/GPU
•
• GA3C A3C
• ( )
batched A2C [4]
batched A2C
• Gorila
• DQN
• Actor Learner
• A3C
•
• GA3C
• GPU
•
•
•
• Gorilla Actor, A3C GA3C ,
•
• Gorila A3C 1
• GA3C ( , )
• Atari SoTa
Parallel Framework for Deep
Reinforcement Learning
A3C on-line experience memory
Algorithm
Experiments
• Atari 12
• Python TensorFlow
•
• 4 (Intel i7-4790K)
• Nvidia 980 Ti GPU
•
• Gorila, A3C, GA3C
• Arch(nips): Conv×2 + FC×2
• Arch(nature): Conv×3 + FC×2 (nips )
Results
The number of actors
Learning rate Actor ( ) 0.0007 . [13]
. .
Time usage in the game of Pong
nips (ne=32) nature 22% , CPU 41%
: GPU
batched A2C
• GPU
• ,
•
•
Ape-X [5]
Ape-X
•
•
• Actor
•
• Experience Replay Memory
• Prioritized Experience Replay
Distributed Prioritized
Experience Replay
Distributed Prioritized
Experience Replay
• Gorila
• Replay Memory
• Actor
• Prioritized DQN …
• 1
• Actor
• Ape-X Actor
Experiments (Ape-X DQN)
• Atari 57
• 12.5K FPS =360Actor×139FPS/4Repeat
• Actor 100
• 19 /sec, 16, 512
• png
• Actor 400 Learner
• Actor ε ( ) ε-greedy
• Experience Replay 20
• 100 FIFO
• Priority Exponent = 0.6, Importance Sampling Exponent = 0.4
Scaling the number of actors
(Ape-X DQN)
Actor
Varying the capacity of the replay
Conclusion
• Prioritized replay
• , SoTa
•
•
•
IMPALA [6]
IMPALA
•
•
• A2C GA3C
• IMPALA
• V-trace
•
• DMLab-30
• Atari57
•
IMPALA
Actor
n …
1. Learner
2. , , LSTM
Learner
Learner
Actor
Learner π Actor μ
( ) V-
trace
GPU
Point: (Actor) (Learner)
A3C . ( )
Efficiency Optimisations
• GPU CPU
• A3C IMPALA
• GA3C, A2C, Ape-X
• TensorFlow
•
• XLA [11]
• cuDNN [12]
V-trace
• Actor Learner
• Actor-Learner
• V-trace Actor-Critic
Notation (MDP)
:
:
:
(Policy μ):
μ
π
V-trace target
•
• Temporal Difference
• Importance Sampling
• (π=μ) =>
n-step
Importance Sampling
• TD
•
• μ π
• 0 behavior policy
• target policy
Retrace
• Retrace[8] ”trace cutting”
•      は時刻tのTDが前回の時刻sの価値関数の更新にど
れだけ影響を与えるか測定する	
• πとμが⼤きく異なれば(オフポリシー)、よりバリアンス(学
習の変動)が⼤きくなる	
•  はバリアンスの削減係数	
• このテクニックを⽤いても収束する値に変化はない
Experiments
•
•
•
• DeepMind Lab 30 , Atari 57
•
Computational Performance
• A3C, Batched A2C (Shallow Model)
Single-Task Training
• 5 DeepMind Lab
• planning task
• maze navigation task × 2
• laser tag task
• simple fruit collection task
•
Convergence and Stability
• 2/5 IMPALA ( )
• V-trace
•
• IMPALA A3C ( )
V-trace Analysis
• No-correction:	No	off-policy	
• ε-correction	
• logπが⼩さくなりすぎないように
勾配計算時に微⼩εを加算
• 1-step	importance	sampling	
• 各ステップで重みをかける	
• V-traceのtraceない版	
• V-trace
V-trace Replay
	
Replay
Multi-Task (Atari)
• Atari 57
• IMPALA A3C
shallow 1 	
IMPALA shallow,	deep 	
A3C
shallow
IMPALA
• IMPALA
•
• オフポリシーアルゴリズムV-trace	
• 他のオフポリシーActor-Critic⼿法と⽐較して安定	
• 実験	
• DMLab-30とAtari57でのマルチタスク学習	
• A3C⽐較して優れたパフォマーンス
Accelerated Methods
for Deep Learning [7]
Accelerated Methods
•
• CPU GPU
•
•
•
•
• Atari
• : NVIDIA DGX-1
• 40 CPU cores, 8P 100GPU
Related Work
• Gorila
• sub-linear
• Ape-X
• prioritized replay
• CPU GPU
• A3C
•
• GA3C
• CPU A3C GPU
•
• IMPALA
• GPU
• V-trace
• PAAC (batched A2C)
• batched A2C
Parallel, Accelerated RL
Framework
•
• …
• CPU
• Deep Neural Network
Synchronized Sampling
• CPU ,
•
• CPU
• CPU
•
サンプリングと推論が交互だが、2グループに分けて処理を進める⼯夫もできる.
Synchronous Multi-GPU
Optimization
• GPU
•
•
• GPU Reduce ( )
•
• NVIDIA Collective Communication Library GPU
Asynchronous Multi-GPU
Optimization
• GPU Sampler Learner
•
1. GPU
2. GPU
3.
• CPU
• 2,3
4. GPU
Experiments
• Atari2600
•
•
• Q
•
Atari Frame Processing
• Minh et al., 2015(Human Level…)
•
• 2
• 2 104×80
•
• Q 3 (DQN-Net)
• 2 (A3C-Net)
Sampling
•
BREAKOUTゲームでの利⽤効率
1 	
.	
	
.
80%
A2C
•
• A2C 0.0007×Num_Actors
シミュレータ数を16~512(バッチサイズを80~2560)に	
増やしていくと、徐々にサンプル効率が悪くなっている
PPO
• PPO (8 ×256=2048)
•
環境1つあたりのバッチサイズを256から4に減らしていった	
並列性を⾼くするとよくなったゲームもあれば悪くなったものもあった
Q-Value Learning with Large
Training Batches
• DQN
• 32 2048 . 512 .
• 32
•
• (2.5, 7.5, 15*10^4)
• Categorical DQN
• DQN 2048
•
Update Rule
• Adam RMSProp
• Categorical DQN, Rainbow RMSProp Adam
• Learner
• RMSProp Adam
Learning Speed
• A2C,A3C,PPO,APPO
• (10 )
• PPO Pong 4
• 256 A2C 25,000 /sec (=90million/hour)
50 million
Policy	Gradient	Learning	
8つのGPUを使って6倍⾼速化
Q-Learning	
50millionステップ達成時間の計測	
DQNでは1GPU,		5CPUで8時間程度	
Categorical-DQNはバッチサイズが⼤き
いため、GPU利⽤の効果が⼤きく出た
Accelerated Methods
• RL
• Q
• …
• Atari
• …
• Atari
•
• Gorila
• DQN
• A3C
• (Actor-Critic)
• GA3C
• ( ) GPU
• batched A2C
•
• Ape-X
• Prioritized Replay
• IMPALA
• Importance Sampling(Retrace)
• Accelerated Methods for Deep Reinforcement Learning
•
• Pong 4 (A3C 4 )
•
•
•
•
• GPU
•
• ,
•
• / Retrace [8]
• (UNREAL) [9]
1. Nair, Arun, et al. “Massively parallel methods for deep reinforcement learning”. arXiv preprint arXiv:
1507.04296, 2015.
2. Mnih, Volodymyr, et al. "Asynchronous methods for deep reinforcement learning". Proceedings of the
33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19-24,
2016, 2016.
3. Babaeizadeh, Mohammad, et al. "GA3C: GPU-based A3C for deep reinforcement learning". NIPS
Workshop, 2016.
4. Clemente, Alfredo V., et al. "Efficient parallel methods for deep reinforcement learning". CoRR, abs/
1705.04862, 2017.
5. Horgan, D., et al. “Distributed Prioritized Experience Replay”. ArXiv e-prints, March 2018.
6. Espeholt, Lasse, et al. "IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner
Architectures”. arXiv preprint arXiv: 1802.01561, 2018
7. Stooke, Adam, Abbeel, Pieter. “Accelerated Methods for Deep Learning”. arXiv preprint arXiv:
1803.02811, 2018
8. Munos, Re ́mi, et al. “Safe and efficient off-policy reinforcement learning”. In Advances in Neural
Information Processing Systems, pp. 1046–1054, 2016.
9. Jaderberg, Max, et al. “Reinforcement learning with unsupervised auxiliary tasks”. International
Conference on Learning Representations, 2017.
10.Dean, Jeffrey, et al. “Large scale distributed deep networks”. In Advances in Neural Information
Processing Systems 25, pp. 1223–1231, 2012.
11.TensorFlow w/XLA: TensorFlow, Compiled!
• https://autodiff-workshop.github.io/slides/JeffDean.pdf
12.Chetlur, Sharan, et al. cudnn: Efficient primitives for deep learning. CoRR, abs/1410.0759, 2014.
13.Goyal, Priya, et al. Accurate, large minibatch sgd: Training imagenet in 1 hour. arXiv preprint
arXiv:1706.02677, 2017.
14.Intuitive RL: Intro to Advantage-Actor-Critic (A2C)
• https://hackernoon.com/intuitive-rl-intro-to-advantage-actor-critic-a2c-4ff545978752

Más contenido relacionado

La actualidad más candente

La actualidad más candente (20)

報酬設計と逆強化学習
報酬設計と逆強化学習報酬設計と逆強化学習
報酬設計と逆強化学習
 
ゼロから始める深層強化学習(NLP2018講演資料)/ Introduction of Deep Reinforcement Learning
ゼロから始める深層強化学習(NLP2018講演資料)/ Introduction of Deep Reinforcement Learningゼロから始める深層強化学習(NLP2018講演資料)/ Introduction of Deep Reinforcement Learning
ゼロから始める深層強化学習(NLP2018講演資料)/ Introduction of Deep Reinforcement Learning
 
方策勾配型強化学習の基礎と応用
方策勾配型強化学習の基礎と応用方策勾配型強化学習の基礎と応用
方策勾配型強化学習の基礎と応用
 
【DL輪読会】マルチエージェント強化学習における近年の 協調的方策学習アルゴリズムの発展
【DL輪読会】マルチエージェント強化学習における近年の 協調的方策学習アルゴリズムの発展【DL輪読会】マルチエージェント強化学習における近年の 協調的方策学習アルゴリズムの発展
【DL輪読会】マルチエージェント強化学習における近年の 協調的方策学習アルゴリズムの発展
 
[DL輪読会]Deep Learning 第15章 表現学習
[DL輪読会]Deep Learning 第15章 表現学習[DL輪読会]Deep Learning 第15章 表現学習
[DL輪読会]Deep Learning 第15章 表現学習
 
強化学習エージェントの内発的動機付けによる探索とその応用(第4回 統計・機械学習若手シンポジウム 招待公演)
強化学習エージェントの内発的動機付けによる探索とその応用(第4回 統計・機械学習若手シンポジウム 招待公演)強化学習エージェントの内発的動機付けによる探索とその応用(第4回 統計・機械学習若手シンポジウム 招待公演)
強化学習エージェントの内発的動機付けによる探索とその応用(第4回 統計・機械学習若手シンポジウム 招待公演)
 
SSII2022 [OS3-02] Federated Learningの基礎と応用
SSII2022 [OS3-02] Federated Learningの基礎と応用SSII2022 [OS3-02] Federated Learningの基礎と応用
SSII2022 [OS3-02] Federated Learningの基礎と応用
 
[DL輪読会]Hindsight Experience Replay
[DL輪読会]Hindsight Experience Replay[DL輪読会]Hindsight Experience Replay
[DL輪読会]Hindsight Experience Replay
 
Mean Teacher
Mean TeacherMean Teacher
Mean Teacher
 
機械学習モデルの判断根拠の説明
機械学習モデルの判断根拠の説明機械学習モデルの判断根拠の説明
機械学習モデルの判断根拠の説明
 
[DL輪読会]近年のオフライン強化学習のまとめ —Offline Reinforcement Learning: Tutorial, Review, an...
[DL輪読会]近年のオフライン強化学習のまとめ —Offline Reinforcement Learning: Tutorial, Review, an...[DL輪読会]近年のオフライン強化学習のまとめ —Offline Reinforcement Learning: Tutorial, Review, an...
[DL輪読会]近年のオフライン強化学習のまとめ —Offline Reinforcement Learning: Tutorial, Review, an...
 
モデル高速化百選
モデル高速化百選モデル高速化百選
モデル高速化百選
 
強化学習 DQNからPPOまで
強化学習 DQNからPPOまで強化学習 DQNからPPOまで
強化学習 DQNからPPOまで
 
近年のHierarchical Vision Transformer
近年のHierarchical Vision Transformer近年のHierarchical Vision Transformer
近年のHierarchical Vision Transformer
 
[DL輪読会]Autonomous Reinforcement Learning: Formalism and Benchmarking
[DL輪読会]Autonomous Reinforcement Learning: Formalism and Benchmarking[DL輪読会]Autonomous Reinforcement Learning: Formalism and Benchmarking
[DL輪読会]Autonomous Reinforcement Learning: Formalism and Benchmarking
 
強化学習その3
強化学習その3強化学習その3
強化学習その3
 
[DL輪読会]Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
[DL輪読会]Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets[DL輪読会]Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
[DL輪読会]Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
 
分散型強化学習手法の最近の動向と分散計算フレームワークRayによる実装の試み
分散型強化学習手法の最近の動向と分散計算フレームワークRayによる実装の試み分散型強化学習手法の最近の動向と分散計算フレームワークRayによる実装の試み
分散型強化学習手法の最近の動向と分散計算フレームワークRayによる実装の試み
 
Skip Connection まとめ(Neural Network)
Skip Connection まとめ(Neural Network)Skip Connection まとめ(Neural Network)
Skip Connection まとめ(Neural Network)
 
SSII2020 [OS2-02] 教師あり事前学習を凌駕する「弱」教師あり事前学習
SSII2020 [OS2-02] 教師あり事前学習を凌駕する「弱」教師あり事前学習SSII2020 [OS2-02] 教師あり事前学習を凌駕する「弱」教師あり事前学習
SSII2020 [OS2-02] 教師あり事前学習を凌駕する「弱」教師あり事前学習
 

Similar a 強化学習の分散アーキテクチャ変遷

Distributed Multi-GPU Computing with Dask, CuPy and RAPIDS
Distributed Multi-GPU Computing with Dask, CuPy and RAPIDSDistributed Multi-GPU Computing with Dask, CuPy and RAPIDS
Distributed Multi-GPU Computing with Dask, CuPy and RAPIDS
PeterAndreasEntschev
 

Similar a 強化学習の分散アーキテクチャ変遷 (20)

181123 asynchronous method for deep reinforcement learning seunghyeok back
181123 asynchronous method for deep reinforcement learning seunghyeok back181123 asynchronous method for deep reinforcement learning seunghyeok back
181123 asynchronous method for deep reinforcement learning seunghyeok back
 
RAPIDS: ускоряем Pandas и scikit-learn на GPU Павел Клеменков, NVidia
RAPIDS: ускоряем Pandas и scikit-learn на GPU  Павел Клеменков, NVidiaRAPIDS: ускоряем Pandas и scikit-learn на GPU  Павел Клеменков, NVidia
RAPIDS: ускоряем Pandas и scikit-learn на GPU Павел Клеменков, NVidia
 
MAtrix Multiplication Parallel.ppsx
MAtrix Multiplication Parallel.ppsxMAtrix Multiplication Parallel.ppsx
MAtrix Multiplication Parallel.ppsx
 
matrixmultiplicationparallel.ppsx
matrixmultiplicationparallel.ppsxmatrixmultiplicationparallel.ppsx
matrixmultiplicationparallel.ppsx
 
IIBMP2019 講演資料「オープンソースで始める深層学習」
IIBMP2019 講演資料「オープンソースで始める深層学習」IIBMP2019 講演資料「オープンソースで始める深層学習」
IIBMP2019 講演資料「オープンソースで始める深層学習」
 
Toronto meetup 20190917
Toronto meetup 20190917Toronto meetup 20190917
Toronto meetup 20190917
 
Getting Started with Keras and TensorFlow - StampedeCon AI Summit 2017
Getting Started with Keras and TensorFlow - StampedeCon AI Summit 2017Getting Started with Keras and TensorFlow - StampedeCon AI Summit 2017
Getting Started with Keras and TensorFlow - StampedeCon AI Summit 2017
 
Using Bayesian Optimization to Tune Machine Learning Models
Using Bayesian Optimization to Tune Machine Learning ModelsUsing Bayesian Optimization to Tune Machine Learning Models
Using Bayesian Optimization to Tune Machine Learning Models
 
Using Bayesian Optimization to Tune Machine Learning Models
Using Bayesian Optimization to Tune Machine Learning ModelsUsing Bayesian Optimization to Tune Machine Learning Models
Using Bayesian Optimization to Tune Machine Learning Models
 
Can FPGAs Compete with GPUs?
Can FPGAs Compete with GPUs?Can FPGAs Compete with GPUs?
Can FPGAs Compete with GPUs?
 
Spark Meetup TensorFrames
Spark Meetup TensorFramesSpark Meetup TensorFrames
Spark Meetup TensorFrames
 
Spark Meetup TensorFrames
Spark Meetup TensorFramesSpark Meetup TensorFrames
Spark Meetup TensorFrames
 
A TRAINING METHOD USING
 DNN-GUIDED LAYERWISE PRETRAINING
 FOR DEEP GAUSSIAN ...
A TRAINING METHOD USING
 DNN-GUIDED LAYERWISE PRETRAINING
 FOR DEEP GAUSSIAN ...A TRAINING METHOD USING
 DNN-GUIDED LAYERWISE PRETRAINING
 FOR DEEP GAUSSIAN ...
A TRAINING METHOD USING
 DNN-GUIDED LAYERWISE PRETRAINING
 FOR DEEP GAUSSIAN ...
 
Image Classification (20230411)
Image Classification (20230411)Image Classification (20230411)
Image Classification (20230411)
 
[DL輪読会]Deep Reinforcement Learning that Matters
[DL輪読会]Deep Reinforcement Learning that Matters[DL輪読会]Deep Reinforcement Learning that Matters
[DL輪読会]Deep Reinforcement Learning that Matters
 
Using SigOpt to Tune Deep Learning Models with Nervana Cloud
Using SigOpt to Tune Deep Learning Models with Nervana CloudUsing SigOpt to Tune Deep Learning Models with Nervana Cloud
Using SigOpt to Tune Deep Learning Models with Nervana Cloud
 
Distributed Multi-GPU Computing with Dask, CuPy and RAPIDS
Distributed Multi-GPU Computing with Dask, CuPy and RAPIDSDistributed Multi-GPU Computing with Dask, CuPy and RAPIDS
Distributed Multi-GPU Computing with Dask, CuPy and RAPIDS
 
Troubleshooting Memory Problems in Java Applications
Troubleshooting Memory Problems in Java ApplicationsTroubleshooting Memory Problems in Java Applications
Troubleshooting Memory Problems in Java Applications
 
【DL輪読会】Toward Fast and Stabilized GAN Training for Highfidelity Few-shot Imag...
【DL輪読会】Toward Fast and Stabilized GAN Training for Highfidelity Few-shot Imag...【DL輪読会】Toward Fast and Stabilized GAN Training for Highfidelity Few-shot Imag...
【DL輪読会】Toward Fast and Stabilized GAN Training for Highfidelity Few-shot Imag...
 
Implementation of linear regression and logistic regression on Spark
Implementation of linear regression and logistic regression on SparkImplementation of linear regression and logistic regression on Spark
Implementation of linear regression and logistic regression on Spark
 

Último

Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
Joaquim Jorge
 

Último (20)

Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a Fresher
 
Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024
 
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivity
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century education
 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : Uncertainty
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organization
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of Terraform
 
Manulife - Insurer Innovation Award 2024
Manulife - Insurer Innovation Award 2024Manulife - Insurer Innovation Award 2024
Manulife - Insurer Innovation Award 2024
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
 
Top 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live StreamsTop 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live Streams
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024
 

強化学習の分散アーキテクチャ変遷