SlideShare a Scribd company logo
BLAZING THE TRAILS BEFORE
BEATING THE PATH:
SAMPLE-EFFICIENT MONTE-
CARLO PLANNING
KATSUKI OHTO
@NIPS2016-YOMI
2017/1/19
INTRODUCED PAPER
• Blazing the trails before beating the path:
Sample - efficient Monte-Carlo planning
(JB. Grill, M. Valko and R. Munos)
• NIPS 2016 accepted paper (poster session)
• Abstract starts with “You are a robot…”
• http://papers.nips.cc/paper/6253-blazing-the-trails-before-
beating-the-path-sample-efficient-monte-carlo-planning
TRAILBLAZER
• Nested-fashion Monte-Carlo Planning Algorithm
• Problem settings:
MDP (contains MAX nodes and AVG nodes)
Actions per each state : Finite
State transition candidates : Finite or Infinite
• Strong theoretical guarantee
MAX
AVG
AIM
• Input : an MDP (Markov Decision Process)
(discount factor 𝛾, maximum number of valid actions 𝐾),
𝜀 (> 0), 𝛿 (0 < 𝛿 < 1)
• Output : estimated value 𝜇 𝜀,𝛿 of current state 𝑠0
• Aim : Get good estimation of real value 𝒱[𝑠0] of current state
such as
ℙ 𝜇 𝜀,𝛿 − 𝒱 𝑠0 > 𝜀 ≤ 𝛿
( ℙ ∙ means probability of ∙ )
with the minimum number of calls to the generative model (state transition function)
1 PLAYER TREE MODEL
IN STOCHASTIC ENVIRONMENT
• Each MAX node means an
opportunity to decide action
• Each AVG node means
stochastic state transition
MAX
AVG
ALGORITHM OVERVIEW
• Global Initialization
set 𝜂, 𝜆 as global value
set 𝑚 as an argument of
root node
• Recursive algorithm
log(𝜂/𝛾)
ALGORITHM OVERVIEW 2
• In both MAX nodes and AVG nodes,
arguments are
𝑚 (desired branching factor)
and
𝜀 (admissible estimation error)
• If 𝑚 is large, we can search many children, but we need much time
(dilemma)
• If 𝜀 is small, we can search deeply, but we need much time (dilemma)
ALGORITHM
FOR AVG NODES
• Input : 𝑚 and 𝜀
• Output : estimated value
• If admissible error 𝜀 is large, ignore
successive reward
• Fill 𝑚 transition samples
(and store immediate reward)
• search all of 𝑚 sampled next states
• return averaged immediate reward +
estimated successive reward
ALGORITHM
FOR MAX NODES
• Input : 𝑚 and 𝜀
• Output : estimated value
• Fill candidate action pool ℒ by all valid actions
• U is a value like standard error of estimation
• Search candidate actions repeatedly until
“Only 1 action left” or “Error might be small”
• If “Error might be small”
then return estimated value of best action
else
search best action 1 more time carefully
SAMPLE COMPLEXITY OF TRAILBLAER
• Sample Complexity is a measure of performance of algorithm
• If N (the number of next states) is finite,
(
1
𝜀
)
max(2,
log 𝑁𝜅
log
1
𝛾
+𝑜 1 )
on condition that 𝜅 ∈ 1, 𝐾 (in detail in
the paper)
else
(
1
𝜀
)2+𝑑
on condition that 𝑑 is a measure of difficulty to identify near-
optimal nodes

More Related Content

What's hot

0415_seminar_DeepDPG
0415_seminar_DeepDPG0415_seminar_DeepDPG
0415_seminar_DeepDPG
Hye-min Ahn
 
Competition winning learning rates
Competition winning learning ratesCompetition winning learning rates
Competition winning learning rates
MLconf
 
Ashfaq Munshi, ML7 Fellow, Pepperdata
Ashfaq Munshi, ML7 Fellow, PepperdataAshfaq Munshi, ML7 Fellow, Pepperdata
Ashfaq Munshi, ML7 Fellow, Pepperdata
MLconf
 
K-Means Algorithm
K-Means AlgorithmK-Means Algorithm
K-Means Algorithm
Carlos Castillo (ChaTo)
 
Dual Learning for Machine Translation (NIPS 2016)
Dual Learning for Machine Translation (NIPS 2016)Dual Learning for Machine Translation (NIPS 2016)
Dual Learning for Machine Translation (NIPS 2016)
Toru Fujino
 
Hyperparameter optimization with approximate gradient
Hyperparameter optimization with approximate gradientHyperparameter optimization with approximate gradient
Hyperparameter optimization with approximate gradient
Fabian Pedregosa
 
Dueling network architectures for deep reinforcement learning
Dueling network architectures for deep reinforcement learningDueling network architectures for deep reinforcement learning
Dueling network architectures for deep reinforcement learning
Taehoon Kim
 
K-Means Clustering Simply
K-Means Clustering SimplyK-Means Clustering Simply
K-Means Clustering Simply
Emad Nabil
 
safe and efficient off policy reinforcement learning
safe and efficient off policy reinforcement learningsafe and efficient off policy reinforcement learning
safe and efficient off policy reinforcement learning
Ryo Iwaki
 
Tutorial on Theory and Application of Generative Adversarial Networks
Tutorial on Theory and Application of Generative Adversarial NetworksTutorial on Theory and Application of Generative Adversarial Networks
Tutorial on Theory and Application of Generative Adversarial Networks
MLReview
 
1118_Seminar_Continuous_Deep Q-Learning with Model based acceleration
1118_Seminar_Continuous_Deep Q-Learning with Model based acceleration1118_Seminar_Continuous_Deep Q-Learning with Model based acceleration
1118_Seminar_Continuous_Deep Q-Learning with Model based acceleration
Hye-min Ahn
 
Variational Autoencoder
Variational AutoencoderVariational Autoencoder
Variational Autoencoder
Mark Chang
 
Gradient Estimation Using Stochastic Computation Graphs
Gradient Estimation Using Stochastic Computation GraphsGradient Estimation Using Stochastic Computation Graphs
Gradient Estimation Using Stochastic Computation Graphs
Yoonho Lee
 
Dr. Erin LeDell, Machine Learning Scientist, H2O.ai at MLconf SEA - 5/20/16
Dr. Erin LeDell, Machine Learning Scientist, H2O.ai at MLconf SEA - 5/20/16Dr. Erin LeDell, Machine Learning Scientist, H2O.ai at MLconf SEA - 5/20/16
Dr. Erin LeDell, Machine Learning Scientist, H2O.ai at MLconf SEA - 5/20/16
MLconf
 
Breaking the Nonsmooth Barrier: A Scalable Parallel Method for Composite Opti...
Breaking the Nonsmooth Barrier: A Scalable Parallel Method for Composite Opti...Breaking the Nonsmooth Barrier: A Scalable Parallel Method for Composite Opti...
Breaking the Nonsmooth Barrier: A Scalable Parallel Method for Composite Opti...
Fabian Pedregosa
 
Speaker Diarization
Speaker DiarizationSpeaker Diarization
Speaker Diarization
HONGJOO LEE
 
ddpg seminar
ddpg seminarddpg seminar
ddpg seminar
민재 정
 
Introduction to Big Data Science
Introduction to Big Data ScienceIntroduction to Big Data Science
Introduction to Big Data Science
Albert Bifet
 
Kmeans initialization
Kmeans initializationKmeans initialization
Kmeans initialization
djempol
 
Melanie Warrick, Deep Learning Engineer, Skymind.io at MLconf SF - 11/13/15
Melanie Warrick, Deep Learning Engineer, Skymind.io at MLconf SF - 11/13/15Melanie Warrick, Deep Learning Engineer, Skymind.io at MLconf SF - 11/13/15
Melanie Warrick, Deep Learning Engineer, Skymind.io at MLconf SF - 11/13/15
MLconf
 

What's hot (20)

0415_seminar_DeepDPG
0415_seminar_DeepDPG0415_seminar_DeepDPG
0415_seminar_DeepDPG
 
Competition winning learning rates
Competition winning learning ratesCompetition winning learning rates
Competition winning learning rates
 
Ashfaq Munshi, ML7 Fellow, Pepperdata
Ashfaq Munshi, ML7 Fellow, PepperdataAshfaq Munshi, ML7 Fellow, Pepperdata
Ashfaq Munshi, ML7 Fellow, Pepperdata
 
K-Means Algorithm
K-Means AlgorithmK-Means Algorithm
K-Means Algorithm
 
Dual Learning for Machine Translation (NIPS 2016)
Dual Learning for Machine Translation (NIPS 2016)Dual Learning for Machine Translation (NIPS 2016)
Dual Learning for Machine Translation (NIPS 2016)
 
Hyperparameter optimization with approximate gradient
Hyperparameter optimization with approximate gradientHyperparameter optimization with approximate gradient
Hyperparameter optimization with approximate gradient
 
Dueling network architectures for deep reinforcement learning
Dueling network architectures for deep reinforcement learningDueling network architectures for deep reinforcement learning
Dueling network architectures for deep reinforcement learning
 
K-Means Clustering Simply
K-Means Clustering SimplyK-Means Clustering Simply
K-Means Clustering Simply
 
safe and efficient off policy reinforcement learning
safe and efficient off policy reinforcement learningsafe and efficient off policy reinforcement learning
safe and efficient off policy reinforcement learning
 
Tutorial on Theory and Application of Generative Adversarial Networks
Tutorial on Theory and Application of Generative Adversarial NetworksTutorial on Theory and Application of Generative Adversarial Networks
Tutorial on Theory and Application of Generative Adversarial Networks
 
1118_Seminar_Continuous_Deep Q-Learning with Model based acceleration
1118_Seminar_Continuous_Deep Q-Learning with Model based acceleration1118_Seminar_Continuous_Deep Q-Learning with Model based acceleration
1118_Seminar_Continuous_Deep Q-Learning with Model based acceleration
 
Variational Autoencoder
Variational AutoencoderVariational Autoencoder
Variational Autoencoder
 
Gradient Estimation Using Stochastic Computation Graphs
Gradient Estimation Using Stochastic Computation GraphsGradient Estimation Using Stochastic Computation Graphs
Gradient Estimation Using Stochastic Computation Graphs
 
Dr. Erin LeDell, Machine Learning Scientist, H2O.ai at MLconf SEA - 5/20/16
Dr. Erin LeDell, Machine Learning Scientist, H2O.ai at MLconf SEA - 5/20/16Dr. Erin LeDell, Machine Learning Scientist, H2O.ai at MLconf SEA - 5/20/16
Dr. Erin LeDell, Machine Learning Scientist, H2O.ai at MLconf SEA - 5/20/16
 
Breaking the Nonsmooth Barrier: A Scalable Parallel Method for Composite Opti...
Breaking the Nonsmooth Barrier: A Scalable Parallel Method for Composite Opti...Breaking the Nonsmooth Barrier: A Scalable Parallel Method for Composite Opti...
Breaking the Nonsmooth Barrier: A Scalable Parallel Method for Composite Opti...
 
Speaker Diarization
Speaker DiarizationSpeaker Diarization
Speaker Diarization
 
ddpg seminar
ddpg seminarddpg seminar
ddpg seminar
 
Introduction to Big Data Science
Introduction to Big Data ScienceIntroduction to Big Data Science
Introduction to Big Data Science
 
Kmeans initialization
Kmeans initializationKmeans initialization
Kmeans initialization
 
Melanie Warrick, Deep Learning Engineer, Skymind.io at MLconf SF - 11/13/15
Melanie Warrick, Deep Learning Engineer, Skymind.io at MLconf SF - 11/13/15Melanie Warrick, Deep Learning Engineer, Skymind.io at MLconf SF - 11/13/15
Melanie Warrick, Deep Learning Engineer, Skymind.io at MLconf SF - 11/13/15
 

Viewers also liked

時系列データ3
時系列データ3時系列データ3
時系列データ3graySpace999
 
Conditional Image Generation with PixelCNN Decoders
Conditional Image Generation with PixelCNN DecodersConditional Image Generation with PixelCNN Decoders
Conditional Image Generation with PixelCNN Decoders
suga93
 
Interaction Networks for Learning about Objects, Relations and Physics
Interaction Networks for Learning about Objects, Relations and PhysicsInteraction Networks for Learning about Objects, Relations and Physics
Interaction Networks for Learning about Objects, Relations and Physics
Ken Kuroki
 
Value iteration networks
Value iteration networksValue iteration networks
Value iteration networks
Fujimoto Keisuke
 
Learning to learn by gradient descent by gradient descent
Learning to learn by gradient descent by gradient descentLearning to learn by gradient descent by gradient descent
Learning to learn by gradient descent by gradient descent
Hiroyuki Fukuda
 
Introduction of “Fairness in Learning: Classic and Contextual Bandits”
Introduction of “Fairness in Learning: Classic and Contextual Bandits”Introduction of “Fairness in Learning: Classic and Contextual Bandits”
Introduction of “Fairness in Learning: Classic and Contextual Bandits”
Kazuto Fukuchi
 
Fast and Probvably Seedings for k-Means
Fast and Probvably Seedings for k-MeansFast and Probvably Seedings for k-Means
Fast and Probvably Seedings for k-Means
Kimikazu Kato
 
[DL輪読会]Convolutional Sequence to Sequence Learning
[DL輪読会]Convolutional Sequence to Sequence Learning[DL輪読会]Convolutional Sequence to Sequence Learning
[DL輪読会]Convolutional Sequence to Sequence Learning
Deep Learning JP
 
論文紹介 Combining Model-Based and Model-Free Updates for Trajectory-Centric Rein...
論文紹介 Combining Model-Based and Model-Free Updates for Trajectory-Centric Rein...論文紹介 Combining Model-Based and Model-Free Updates for Trajectory-Centric Rein...
論文紹介 Combining Model-Based and Model-Free Updates for Trajectory-Centric Rein...
Kusano Hitoshi
 
NIPS 2016 Overview and Deep Learning Topics
NIPS 2016 Overview and Deep Learning Topics  NIPS 2016 Overview and Deep Learning Topics
NIPS 2016 Overview and Deep Learning Topics
Koichi Hamada
 
Matching networks for one shot learning
Matching networks for one shot learningMatching networks for one shot learning
Matching networks for one shot learning
Kazuki Fujikawa
 
ICML2016読み会 概要紹介
ICML2016読み会 概要紹介ICML2016読み会 概要紹介
ICML2016読み会 概要紹介
Kohei Hayashi
 
論文紹介 Pixel Recurrent Neural Networks
論文紹介 Pixel Recurrent Neural Networks論文紹介 Pixel Recurrent Neural Networks
論文紹介 Pixel Recurrent Neural Networks
Seiya Tokui
 

Viewers also liked (13)

時系列データ3
時系列データ3時系列データ3
時系列データ3
 
Conditional Image Generation with PixelCNN Decoders
Conditional Image Generation with PixelCNN DecodersConditional Image Generation with PixelCNN Decoders
Conditional Image Generation with PixelCNN Decoders
 
Interaction Networks for Learning about Objects, Relations and Physics
Interaction Networks for Learning about Objects, Relations and PhysicsInteraction Networks for Learning about Objects, Relations and Physics
Interaction Networks for Learning about Objects, Relations and Physics
 
Value iteration networks
Value iteration networksValue iteration networks
Value iteration networks
 
Learning to learn by gradient descent by gradient descent
Learning to learn by gradient descent by gradient descentLearning to learn by gradient descent by gradient descent
Learning to learn by gradient descent by gradient descent
 
Introduction of “Fairness in Learning: Classic and Contextual Bandits”
Introduction of “Fairness in Learning: Classic and Contextual Bandits”Introduction of “Fairness in Learning: Classic and Contextual Bandits”
Introduction of “Fairness in Learning: Classic and Contextual Bandits”
 
Fast and Probvably Seedings for k-Means
Fast and Probvably Seedings for k-MeansFast and Probvably Seedings for k-Means
Fast and Probvably Seedings for k-Means
 
[DL輪読会]Convolutional Sequence to Sequence Learning
[DL輪読会]Convolutional Sequence to Sequence Learning[DL輪読会]Convolutional Sequence to Sequence Learning
[DL輪読会]Convolutional Sequence to Sequence Learning
 
論文紹介 Combining Model-Based and Model-Free Updates for Trajectory-Centric Rein...
論文紹介 Combining Model-Based and Model-Free Updates for Trajectory-Centric Rein...論文紹介 Combining Model-Based and Model-Free Updates for Trajectory-Centric Rein...
論文紹介 Combining Model-Based and Model-Free Updates for Trajectory-Centric Rein...
 
NIPS 2016 Overview and Deep Learning Topics
NIPS 2016 Overview and Deep Learning Topics  NIPS 2016 Overview and Deep Learning Topics
NIPS 2016 Overview and Deep Learning Topics
 
Matching networks for one shot learning
Matching networks for one shot learningMatching networks for one shot learning
Matching networks for one shot learning
 
ICML2016読み会 概要紹介
ICML2016読み会 概要紹介ICML2016読み会 概要紹介
ICML2016読み会 概要紹介
 
論文紹介 Pixel Recurrent Neural Networks
論文紹介 Pixel Recurrent Neural Networks論文紹介 Pixel Recurrent Neural Networks
論文紹介 Pixel Recurrent Neural Networks
 

Similar to Introduction of "TrailBlazer" algorithm

Performance OR Capacity #CMGimPACt2016
Performance OR Capacity #CMGimPACt2016 Performance OR Capacity #CMGimPACt2016
Performance OR Capacity #CMGimPACt2016
Alex Gilgur
 
Introduction to Genetic algorithm and its significance in VLSI design and aut...
Introduction to Genetic algorithm and its significance in VLSI design and aut...Introduction to Genetic algorithm and its significance in VLSI design and aut...
Introduction to Genetic algorithm and its significance in VLSI design and aut...
Centre for Electronics, Computer, Self development
 
Artificial Intelligence Course: Linear models
Artificial Intelligence Course: Linear models Artificial Intelligence Course: Linear models
Artificial Intelligence Course: Linear models
ananth
 
Design and Analysis of Algorithms.pptx
Design and Analysis of Algorithms.pptxDesign and Analysis of Algorithms.pptx
Design and Analysis of Algorithms.pptx
Syed Zaid Irshad
 
XGBoost: the algorithm that wins every competition
XGBoost: the algorithm that wins every competitionXGBoost: the algorithm that wins every competition
XGBoost: the algorithm that wins every competition
Jaroslaw Szymczak
 
STUDY ON PROJECT MANAGEMENT THROUGH GENETIC ALGORITHM
STUDY ON PROJECT MANAGEMENT THROUGH GENETIC ALGORITHMSTUDY ON PROJECT MANAGEMENT THROUGH GENETIC ALGORITHM
STUDY ON PROJECT MANAGEMENT THROUGH GENETIC ALGORITHM
Avay Minni
 
Data Structures - Lecture 1 [introduction]
Data Structures - Lecture 1 [introduction]Data Structures - Lecture 1 [introduction]
Data Structures - Lecture 1 [introduction]
Muhammad Hammad Waseem
 
DutchMLSchool 2022 - History and Developments in ML
DutchMLSchool 2022 - History and Developments in MLDutchMLSchool 2022 - History and Developments in ML
DutchMLSchool 2022 - History and Developments in ML
BigML, Inc
 
Reinfrocement Learning
Reinfrocement LearningReinfrocement Learning
Reinfrocement Learning
Natan Katz
 
Final Presentation - Edan&Itzik
Final Presentation - Edan&ItzikFinal Presentation - Edan&Itzik
Final Presentation - Edan&Itzik
itzik cohen
 
General Tips for participating Kaggle Competitions
General Tips for participating Kaggle CompetitionsGeneral Tips for participating Kaggle Competitions
General Tips for participating Kaggle Competitions
Mark Peng
 
EMOD_Optimization_Presentation.pptx
EMOD_Optimization_Presentation.pptxEMOD_Optimization_Presentation.pptx
EMOD_Optimization_Presentation.pptx
AliElMoselhy
 
Practical deep learning for computer vision
Practical deep learning for computer visionPractical deep learning for computer vision
Practical deep learning for computer vision
Eran Shlomo
 
Deep Convolutional GANs - meaning of latent space
Deep Convolutional GANs - meaning of latent spaceDeep Convolutional GANs - meaning of latent space
Deep Convolutional GANs - meaning of latent space
Hansol Kang
 
Mini datathon
Mini datathonMini datathon
Mini datathon
Kunal Jain
 
Foundations: Artificial Neural Networks
Foundations: Artificial Neural NetworksFoundations: Artificial Neural Networks
Foundations: Artificial Neural Networks
ananth
 
Ga presentation
Ga presentationGa presentation
Ga presentation
ziad zohdy
 
Scaling out logistic regression with Spark
Scaling out logistic regression with SparkScaling out logistic regression with Spark
Scaling out logistic regression with Spark
Barak Gitsis
 
Synthesis of analytical methods data driven decision-making
Synthesis of analytical methods data driven decision-makingSynthesis of analytical methods data driven decision-making
Synthesis of analytical methods data driven decision-making
Adam Doyle
 
Introduction to Deep Reinforcement Learning
Introduction to Deep Reinforcement LearningIntroduction to Deep Reinforcement Learning
Introduction to Deep Reinforcement Learning
IDEAS - Int'l Data Engineering and Science Association
 

Similar to Introduction of "TrailBlazer" algorithm (20)

Performance OR Capacity #CMGimPACt2016
Performance OR Capacity #CMGimPACt2016 Performance OR Capacity #CMGimPACt2016
Performance OR Capacity #CMGimPACt2016
 
Introduction to Genetic algorithm and its significance in VLSI design and aut...
Introduction to Genetic algorithm and its significance in VLSI design and aut...Introduction to Genetic algorithm and its significance in VLSI design and aut...
Introduction to Genetic algorithm and its significance in VLSI design and aut...
 
Artificial Intelligence Course: Linear models
Artificial Intelligence Course: Linear models Artificial Intelligence Course: Linear models
Artificial Intelligence Course: Linear models
 
Design and Analysis of Algorithms.pptx
Design and Analysis of Algorithms.pptxDesign and Analysis of Algorithms.pptx
Design and Analysis of Algorithms.pptx
 
XGBoost: the algorithm that wins every competition
XGBoost: the algorithm that wins every competitionXGBoost: the algorithm that wins every competition
XGBoost: the algorithm that wins every competition
 
STUDY ON PROJECT MANAGEMENT THROUGH GENETIC ALGORITHM
STUDY ON PROJECT MANAGEMENT THROUGH GENETIC ALGORITHMSTUDY ON PROJECT MANAGEMENT THROUGH GENETIC ALGORITHM
STUDY ON PROJECT MANAGEMENT THROUGH GENETIC ALGORITHM
 
Data Structures - Lecture 1 [introduction]
Data Structures - Lecture 1 [introduction]Data Structures - Lecture 1 [introduction]
Data Structures - Lecture 1 [introduction]
 
DutchMLSchool 2022 - History and Developments in ML
DutchMLSchool 2022 - History and Developments in MLDutchMLSchool 2022 - History and Developments in ML
DutchMLSchool 2022 - History and Developments in ML
 
Reinfrocement Learning
Reinfrocement LearningReinfrocement Learning
Reinfrocement Learning
 
Final Presentation - Edan&Itzik
Final Presentation - Edan&ItzikFinal Presentation - Edan&Itzik
Final Presentation - Edan&Itzik
 
General Tips for participating Kaggle Competitions
General Tips for participating Kaggle CompetitionsGeneral Tips for participating Kaggle Competitions
General Tips for participating Kaggle Competitions
 
EMOD_Optimization_Presentation.pptx
EMOD_Optimization_Presentation.pptxEMOD_Optimization_Presentation.pptx
EMOD_Optimization_Presentation.pptx
 
Practical deep learning for computer vision
Practical deep learning for computer visionPractical deep learning for computer vision
Practical deep learning for computer vision
 
Deep Convolutional GANs - meaning of latent space
Deep Convolutional GANs - meaning of latent spaceDeep Convolutional GANs - meaning of latent space
Deep Convolutional GANs - meaning of latent space
 
Mini datathon
Mini datathonMini datathon
Mini datathon
 
Foundations: Artificial Neural Networks
Foundations: Artificial Neural NetworksFoundations: Artificial Neural Networks
Foundations: Artificial Neural Networks
 
Ga presentation
Ga presentationGa presentation
Ga presentation
 
Scaling out logistic regression with Spark
Scaling out logistic regression with SparkScaling out logistic regression with Spark
Scaling out logistic regression with Spark
 
Synthesis of analytical methods data driven decision-making
Synthesis of analytical methods data driven decision-makingSynthesis of analytical methods data driven decision-making
Synthesis of analytical methods data driven decision-making
 
Introduction to Deep Reinforcement Learning
Introduction to Deep Reinforcement LearningIntroduction to Deep Reinforcement Learning
Introduction to Deep Reinforcement Learning
 

More from Katsuki Ohto

論文紹介 Anomaly Detection using One-Class Neural Networks (修正版
論文紹介 Anomaly Detection using One-Class Neural Networks (修正版論文紹介 Anomaly Detection using One-Class Neural Networks (修正版
論文紹介 Anomaly Detection using One-Class Neural Networks (修正版
Katsuki Ohto
 
ゲームAIを学んで1000年生きた話
ゲームAIを学んで1000年生きた話ゲームAIを学んで1000年生きた話
ゲームAIを学んで1000年生きた話
Katsuki Ohto
 
Tensorflowユーザから見た Alpha(Go)Zero, Ponanza (TFUG #7)
Tensorflowユーザから見た Alpha(Go)Zero, Ponanza (TFUG #7)Tensorflowユーザから見た Alpha(Go)Zero, Ponanza (TFUG #7)
Tensorflowユーザから見た Alpha(Go)Zero, Ponanza (TFUG #7)
Katsuki Ohto
 
論文紹介: Value Prediction Network
論文紹介: Value Prediction Network論文紹介: Value Prediction Network
論文紹介: Value Prediction Network
Katsuki Ohto
 
将棋ニューラルネットとこれからのゲームAI
将棋ニューラルネットとこれからのゲームAI将棋ニューラルネットとこれからのゲームAI
将棋ニューラルネットとこれからのゲームAI
Katsuki Ohto
 
大富豪に対する機械学習の適用 + α
大富豪に対する機械学習の適用 + α大富豪に対する機械学習の適用 + α
大富豪に対する機械学習の適用 + α
Katsuki Ohto
 
論文紹介 : Unifying count based exploration and intrinsic motivation
論文紹介 : Unifying count based exploration and intrinsic motivation論文紹介 : Unifying count based exploration and intrinsic motivation
論文紹介 : Unifying count based exploration and intrinsic motivation
Katsuki Ohto
 
カーリングの局面評価関数を学習 WITH “TENSOR FLOW”
カーリングの局面評価関数を学習 WITH “TENSOR FLOW”カーリングの局面評価関数を学習 WITH “TENSOR FLOW”
カーリングの局面評価関数を学習 WITH “TENSOR FLOW”
Katsuki Ohto
 

More from Katsuki Ohto (8)

論文紹介 Anomaly Detection using One-Class Neural Networks (修正版
論文紹介 Anomaly Detection using One-Class Neural Networks (修正版論文紹介 Anomaly Detection using One-Class Neural Networks (修正版
論文紹介 Anomaly Detection using One-Class Neural Networks (修正版
 
ゲームAIを学んで1000年生きた話
ゲームAIを学んで1000年生きた話ゲームAIを学んで1000年生きた話
ゲームAIを学んで1000年生きた話
 
Tensorflowユーザから見た Alpha(Go)Zero, Ponanza (TFUG #7)
Tensorflowユーザから見た Alpha(Go)Zero, Ponanza (TFUG #7)Tensorflowユーザから見た Alpha(Go)Zero, Ponanza (TFUG #7)
Tensorflowユーザから見た Alpha(Go)Zero, Ponanza (TFUG #7)
 
論文紹介: Value Prediction Network
論文紹介: Value Prediction Network論文紹介: Value Prediction Network
論文紹介: Value Prediction Network
 
将棋ニューラルネットとこれからのゲームAI
将棋ニューラルネットとこれからのゲームAI将棋ニューラルネットとこれからのゲームAI
将棋ニューラルネットとこれからのゲームAI
 
大富豪に対する機械学習の適用 + α
大富豪に対する機械学習の適用 + α大富豪に対する機械学習の適用 + α
大富豪に対する機械学習の適用 + α
 
論文紹介 : Unifying count based exploration and intrinsic motivation
論文紹介 : Unifying count based exploration and intrinsic motivation論文紹介 : Unifying count based exploration and intrinsic motivation
論文紹介 : Unifying count based exploration and intrinsic motivation
 
カーリングの局面評価関数を学習 WITH “TENSOR FLOW”
カーリングの局面評価関数を学習 WITH “TENSOR FLOW”カーリングの局面評価関数を学習 WITH “TENSOR FLOW”
カーリングの局面評価関数を学習 WITH “TENSOR FLOW”
 

Recently uploaded

5th LF Energy Power Grid Model Meet-up Slides
5th LF Energy Power Grid Model Meet-up Slides5th LF Energy Power Grid Model Meet-up Slides
5th LF Energy Power Grid Model Meet-up Slides
DanBrown980551
 
Freshworks Rethinks NoSQL for Rapid Scaling & Cost-Efficiency
Freshworks Rethinks NoSQL for Rapid Scaling & Cost-EfficiencyFreshworks Rethinks NoSQL for Rapid Scaling & Cost-Efficiency
Freshworks Rethinks NoSQL for Rapid Scaling & Cost-Efficiency
ScyllaDB
 
Taking AI to the Next Level in Manufacturing.pdf
Taking AI to the Next Level in Manufacturing.pdfTaking AI to the Next Level in Manufacturing.pdf
Taking AI to the Next Level in Manufacturing.pdf
ssuserfac0301
 
JavaLand 2024: Application Development Green Masterplan
JavaLand 2024: Application Development Green MasterplanJavaLand 2024: Application Development Green Masterplan
JavaLand 2024: Application Development Green Masterplan
Miro Wengner
 
Your One-Stop Shop for Python Success: Top 10 US Python Development Providers
Your One-Stop Shop for Python Success: Top 10 US Python Development ProvidersYour One-Stop Shop for Python Success: Top 10 US Python Development Providers
Your One-Stop Shop for Python Success: Top 10 US Python Development Providers
akankshawande
 
"Scaling RAG Applications to serve millions of users", Kevin Goedecke
"Scaling RAG Applications to serve millions of users",  Kevin Goedecke"Scaling RAG Applications to serve millions of users",  Kevin Goedecke
"Scaling RAG Applications to serve millions of users", Kevin Goedecke
Fwdays
 
Nordic Marketo Engage User Group_June 13_ 2024.pptx
Nordic Marketo Engage User Group_June 13_ 2024.pptxNordic Marketo Engage User Group_June 13_ 2024.pptx
Nordic Marketo Engage User Group_June 13_ 2024.pptx
MichaelKnudsen27
 
"Frontline Battles with DDoS: Best practices and Lessons Learned", Igor Ivaniuk
"Frontline Battles with DDoS: Best practices and Lessons Learned",  Igor Ivaniuk"Frontline Battles with DDoS: Best practices and Lessons Learned",  Igor Ivaniuk
"Frontline Battles with DDoS: Best practices and Lessons Learned", Igor Ivaniuk
Fwdays
 
Christine's Supplier Sourcing Presentaion.pptx
Christine's Supplier Sourcing Presentaion.pptxChristine's Supplier Sourcing Presentaion.pptx
Christine's Supplier Sourcing Presentaion.pptx
christinelarrosa
 
Y-Combinator seed pitch deck template PP
Y-Combinator seed pitch deck template PPY-Combinator seed pitch deck template PP
Y-Combinator seed pitch deck template PP
c5vrf27qcz
 
The Microsoft 365 Migration Tutorial For Beginner.pptx
The Microsoft 365 Migration Tutorial For Beginner.pptxThe Microsoft 365 Migration Tutorial For Beginner.pptx
The Microsoft 365 Migration Tutorial For Beginner.pptx
operationspcvita
 
What is an RPA CoE? Session 1 – CoE Vision
What is an RPA CoE?  Session 1 – CoE VisionWhat is an RPA CoE?  Session 1 – CoE Vision
What is an RPA CoE? Session 1 – CoE Vision
DianaGray10
 
zkStudyClub - LatticeFold: A Lattice-based Folding Scheme and its Application...
zkStudyClub - LatticeFold: A Lattice-based Folding Scheme and its Application...zkStudyClub - LatticeFold: A Lattice-based Folding Scheme and its Application...
zkStudyClub - LatticeFold: A Lattice-based Folding Scheme and its Application...
Alex Pruden
 
Leveraging the Graph for Clinical Trials and Standards
Leveraging the Graph for Clinical Trials and StandardsLeveraging the Graph for Clinical Trials and Standards
Leveraging the Graph for Clinical Trials and Standards
Neo4j
 
A Deep Dive into ScyllaDB's Architecture
A Deep Dive into ScyllaDB's ArchitectureA Deep Dive into ScyllaDB's Architecture
A Deep Dive into ScyllaDB's Architecture
ScyllaDB
 
PRODUCT LISTING OPTIMIZATION PRESENTATION.pptx
PRODUCT LISTING OPTIMIZATION PRESENTATION.pptxPRODUCT LISTING OPTIMIZATION PRESENTATION.pptx
PRODUCT LISTING OPTIMIZATION PRESENTATION.pptx
christinelarrosa
 
Northern Engraving | Nameplate Manufacturing Process - 2024
Northern Engraving | Nameplate Manufacturing Process - 2024Northern Engraving | Nameplate Manufacturing Process - 2024
Northern Engraving | Nameplate Manufacturing Process - 2024
Northern Engraving
 
Introduction of Cybersecurity with OSS at Code Europe 2024
Introduction of Cybersecurity with OSS  at Code Europe 2024Introduction of Cybersecurity with OSS  at Code Europe 2024
Introduction of Cybersecurity with OSS at Code Europe 2024
Hiroshi SHIBATA
 
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdfHow to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
Chart Kalyan
 
Christine's Product Research Presentation.pptx
Christine's Product Research Presentation.pptxChristine's Product Research Presentation.pptx
Christine's Product Research Presentation.pptx
christinelarrosa
 

Recently uploaded (20)

5th LF Energy Power Grid Model Meet-up Slides
5th LF Energy Power Grid Model Meet-up Slides5th LF Energy Power Grid Model Meet-up Slides
5th LF Energy Power Grid Model Meet-up Slides
 
Freshworks Rethinks NoSQL for Rapid Scaling & Cost-Efficiency
Freshworks Rethinks NoSQL for Rapid Scaling & Cost-EfficiencyFreshworks Rethinks NoSQL for Rapid Scaling & Cost-Efficiency
Freshworks Rethinks NoSQL for Rapid Scaling & Cost-Efficiency
 
Taking AI to the Next Level in Manufacturing.pdf
Taking AI to the Next Level in Manufacturing.pdfTaking AI to the Next Level in Manufacturing.pdf
Taking AI to the Next Level in Manufacturing.pdf
 
JavaLand 2024: Application Development Green Masterplan
JavaLand 2024: Application Development Green MasterplanJavaLand 2024: Application Development Green Masterplan
JavaLand 2024: Application Development Green Masterplan
 
Your One-Stop Shop for Python Success: Top 10 US Python Development Providers
Your One-Stop Shop for Python Success: Top 10 US Python Development ProvidersYour One-Stop Shop for Python Success: Top 10 US Python Development Providers
Your One-Stop Shop for Python Success: Top 10 US Python Development Providers
 
"Scaling RAG Applications to serve millions of users", Kevin Goedecke
"Scaling RAG Applications to serve millions of users",  Kevin Goedecke"Scaling RAG Applications to serve millions of users",  Kevin Goedecke
"Scaling RAG Applications to serve millions of users", Kevin Goedecke
 
Nordic Marketo Engage User Group_June 13_ 2024.pptx
Nordic Marketo Engage User Group_June 13_ 2024.pptxNordic Marketo Engage User Group_June 13_ 2024.pptx
Nordic Marketo Engage User Group_June 13_ 2024.pptx
 
"Frontline Battles with DDoS: Best practices and Lessons Learned", Igor Ivaniuk
"Frontline Battles with DDoS: Best practices and Lessons Learned",  Igor Ivaniuk"Frontline Battles with DDoS: Best practices and Lessons Learned",  Igor Ivaniuk
"Frontline Battles with DDoS: Best practices and Lessons Learned", Igor Ivaniuk
 
Christine's Supplier Sourcing Presentaion.pptx
Christine's Supplier Sourcing Presentaion.pptxChristine's Supplier Sourcing Presentaion.pptx
Christine's Supplier Sourcing Presentaion.pptx
 
Y-Combinator seed pitch deck template PP
Y-Combinator seed pitch deck template PPY-Combinator seed pitch deck template PP
Y-Combinator seed pitch deck template PP
 
The Microsoft 365 Migration Tutorial For Beginner.pptx
The Microsoft 365 Migration Tutorial For Beginner.pptxThe Microsoft 365 Migration Tutorial For Beginner.pptx
The Microsoft 365 Migration Tutorial For Beginner.pptx
 
What is an RPA CoE? Session 1 – CoE Vision
What is an RPA CoE?  Session 1 – CoE VisionWhat is an RPA CoE?  Session 1 – CoE Vision
What is an RPA CoE? Session 1 – CoE Vision
 
zkStudyClub - LatticeFold: A Lattice-based Folding Scheme and its Application...
zkStudyClub - LatticeFold: A Lattice-based Folding Scheme and its Application...zkStudyClub - LatticeFold: A Lattice-based Folding Scheme and its Application...
zkStudyClub - LatticeFold: A Lattice-based Folding Scheme and its Application...
 
Leveraging the Graph for Clinical Trials and Standards
Leveraging the Graph for Clinical Trials and StandardsLeveraging the Graph for Clinical Trials and Standards
Leveraging the Graph for Clinical Trials and Standards
 
A Deep Dive into ScyllaDB's Architecture
A Deep Dive into ScyllaDB's ArchitectureA Deep Dive into ScyllaDB's Architecture
A Deep Dive into ScyllaDB's Architecture
 
PRODUCT LISTING OPTIMIZATION PRESENTATION.pptx
PRODUCT LISTING OPTIMIZATION PRESENTATION.pptxPRODUCT LISTING OPTIMIZATION PRESENTATION.pptx
PRODUCT LISTING OPTIMIZATION PRESENTATION.pptx
 
Northern Engraving | Nameplate Manufacturing Process - 2024
Northern Engraving | Nameplate Manufacturing Process - 2024Northern Engraving | Nameplate Manufacturing Process - 2024
Northern Engraving | Nameplate Manufacturing Process - 2024
 
Introduction of Cybersecurity with OSS at Code Europe 2024
Introduction of Cybersecurity with OSS  at Code Europe 2024Introduction of Cybersecurity with OSS  at Code Europe 2024
Introduction of Cybersecurity with OSS at Code Europe 2024
 
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdfHow to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
 
Christine's Product Research Presentation.pptx
Christine's Product Research Presentation.pptxChristine's Product Research Presentation.pptx
Christine's Product Research Presentation.pptx
 

Introduction of "TrailBlazer" algorithm

  • 1. BLAZING THE TRAILS BEFORE BEATING THE PATH: SAMPLE-EFFICIENT MONTE- CARLO PLANNING KATSUKI OHTO @NIPS2016-YOMI 2017/1/19
  • 2. INTRODUCED PAPER • Blazing the trails before beating the path: Sample - efficient Monte-Carlo planning (JB. Grill, M. Valko and R. Munos) • NIPS 2016 accepted paper (poster session) • Abstract starts with “You are a robot…” • http://papers.nips.cc/paper/6253-blazing-the-trails-before- beating-the-path-sample-efficient-monte-carlo-planning
  • 3. TRAILBLAZER • Nested-fashion Monte-Carlo Planning Algorithm • Problem settings: MDP (contains MAX nodes and AVG nodes) Actions per each state : Finite State transition candidates : Finite or Infinite • Strong theoretical guarantee MAX AVG
  • 4. AIM • Input : an MDP (Markov Decision Process) (discount factor 𝛾, maximum number of valid actions 𝐾), 𝜀 (> 0), 𝛿 (0 < 𝛿 < 1) • Output : estimated value 𝜇 𝜀,𝛿 of current state 𝑠0 • Aim : Get good estimation of real value 𝒱[𝑠0] of current state such as ℙ 𝜇 𝜀,𝛿 − 𝒱 𝑠0 > 𝜀 ≤ 𝛿 ( ℙ ∙ means probability of ∙ ) with the minimum number of calls to the generative model (state transition function)
  • 5. 1 PLAYER TREE MODEL IN STOCHASTIC ENVIRONMENT • Each MAX node means an opportunity to decide action • Each AVG node means stochastic state transition MAX AVG
  • 6. ALGORITHM OVERVIEW • Global Initialization set 𝜂, 𝜆 as global value set 𝑚 as an argument of root node • Recursive algorithm log(𝜂/𝛾)
  • 7. ALGORITHM OVERVIEW 2 • In both MAX nodes and AVG nodes, arguments are 𝑚 (desired branching factor) and 𝜀 (admissible estimation error) • If 𝑚 is large, we can search many children, but we need much time (dilemma) • If 𝜀 is small, we can search deeply, but we need much time (dilemma)
  • 8. ALGORITHM FOR AVG NODES • Input : 𝑚 and 𝜀 • Output : estimated value • If admissible error 𝜀 is large, ignore successive reward • Fill 𝑚 transition samples (and store immediate reward) • search all of 𝑚 sampled next states • return averaged immediate reward + estimated successive reward
  • 9. ALGORITHM FOR MAX NODES • Input : 𝑚 and 𝜀 • Output : estimated value • Fill candidate action pool ℒ by all valid actions • U is a value like standard error of estimation • Search candidate actions repeatedly until “Only 1 action left” or “Error might be small” • If “Error might be small” then return estimated value of best action else search best action 1 more time carefully
  • 10. SAMPLE COMPLEXITY OF TRAILBLAER • Sample Complexity is a measure of performance of algorithm • If N (the number of next states) is finite, ( 1 𝜀 ) max(2, log 𝑁𝜅 log 1 𝛾 +𝑜 1 ) on condition that 𝜅 ∈ 1, 𝐾 (in detail in the paper) else ( 1 𝜀 )2+𝑑 on condition that 𝑑 is a measure of difficulty to identify near- optimal nodes