Value iteration networks

Fujimoto Keisuke
Fujimoto KeisukeABEJA, Inc.
Value	Iteration	Networks
A.	Tamar,	Y.	Wu,	G.	Thomas,	S.	Levine,	and	P.	Abbeel
Dept.	of	Electrical	Engineering	and	Computer	Sciences,	UC	Berkeley
Presenter:	Keisuke	Fujimoto
(Twitter	@peisuke)
Value	Iteration	Networks
Purpose: Machine	learning	based	robot	path	planning.	This	planner	is	available	in	
new	environment not	included	in	train	data	set.
Strategy: Prediction	of	optimal	action.	The	method	can	learn	rewards	of	each	place	
and	action	to	get	good	rewards.
Result: Planning	in	28	x	28	grid	map,	Applicable	to	continuous	control	robot	
Map
Pose
Velocity
Goal
Action
A.	Tamar,	Y.	Wu,	G.	Thomas,	S.	Levine,	and	P.	Abbeel
Dept.	of	Electrical	Engineering	and	Computer	Sciences,	UC	Berkeley
Presenter:	
Keisuke	Fujimoto
(ABEJA)
Background
Target	:	Autonomous	Robot
• Manipulation	robot,	Navigation	robot,	Transfer	robot
Problem	:	
• Reinforcement	learning	can	not	work	outside	of	training	
environments.	
Goal
Target	object
Manipulation	robot Navigation	robot
Contribution
• Value	Iteration	Networks	(VIN)
• Model	free	training
• It	does	not	require	robot	dynamics	models.
• Generalized	action	prediction	in	new	environments
• It	can	not	work	outside	of	training	environments.
• Key	approach
• Represents	value-iteration	planning	by	CNN
• Prediction	of	reward	map	and	computation	of	sum	
of	future	rewards.
Overview	of	VIN
Input	:	State	of	the	robot	(pose,	velocity),	goal,	map	(left	fig.)
Output	:	Action	(direction,	mortar's	torque)
Strategy	:	Determination	of	optimal	action	using	predicted		
rewards	(right	fig.).
State Rewards
Reward	propagation
• Action	can	be	determined	by	sum	
of	future	reward	generated	using	
reward	propagation
-10 -10 -10
-10 -10 1
-10 -10
Map Reward	from	map
Left	move	action
-10 -10 -9 -10
-10 -10 -9 1 0.9
-10 -10 -9
-10 -10 -10
-10 -10 1 -9
-9 -10 -10 0.9
-9 -9
Up	move	from	map
One-step	propagation	example:
Determination	of	action
• Optimal	action	at	reward	propagated	
place	is	max	reward	action	(middle	fig.)
• Determination	of	optimal	action	using	
propagated	reward	(right	fig.)
Left	move	action
-10 -10 -9 -10
-10 -10 -9 1 0.9
-10 -10 -9
-10 -10 -10
-10 -10 1 -9
-9 -10 -10 0.9
-9 -9
Up	move	from	map -10 -10 -9 -10
-10 -10 -9 1 0.9
-9 -10 -10 0.9
-9 -9
Max
After	Reward	propagation	
-10 -10 -9 -8 -10
-10 -10 -9 1 0.9
-9 -10 -10 0.9 0.8
-8 -9 -9 0.8 0.7
-7 -8 -8 0.7 0.6
Current	robot	pose
Value	Iteration	Module
• Reward	propagation	with	Convolutional	Neural	Network
• Input	is	reward	map	and	output	is	sum	of	feature	reward	map
• Q	is	hidden	reward	map,	V	is	sum	of	feature	reward	map
Output
Convolution
Max
Value	Iteration	Networks
• Deep	Architecture	of	Value	Iteration	Networks
• Input	is	map	and	state,	fR predicts	reward	map
• Attention	modules	crops	the	value	map	around	robot	position
• 𝜓 outputs	optimal	action
Attention	function
• Attention	module	crops	a	subset	of	the	values	around	
current	robot	pose.
• Optimal	pose	have	relative	to	only	current	robot	pose.
• Due	to	this	attention	module,	prediction	of	optimal	
action	becomes	easy.
-10 -10 -9 -8 -10
-10 -10 -9 1 0.9
-9 -10 -10 0.9 0.8
-8 -9 -9 0.8 0.7
-7 -8 -8 0.7 0.6
If	robot	is	here.
-10 0.9 0.8
-9 0.8 0.7
-8 0.7 0.6
Selected	area
Grid-World	Domain
Environment	:
Occupancy	grid	map,	test	size	is	8x8	to	28x28
The	number	of	recurrence	is	20	for	the	28x28	maps
Training	dataset	is	5000	maps,	7	trajectories.
Networks	Arch.	:	
Competitive	method	:
CNN	based	Deep	Q-Network,	Direct	action	prediction	using	FCN	
Map,	Goal
CNN Reward	map VI	module Attention FC	layer
Action
Current	Position
3	layer	net
150	hidden	node 10	channels	in	Q-layer 80	parameters
Results	of	Grid-World	Domain
Predicted	path Reward Sum	of	feature	reward
Mars	Rover	Navigation
Environment	:
• Navigating	the	surface	of	Mars	by	a	rover.
• It	predicts	path	from	only	surface	image	without	obstacle	
information.
• Success	rate	is	90.3%.
Red	point	shows	elevation	sharper,	in	prediction	time,	vin	
does	not	uses	the	elevation	shape	information
Continuous	Control
Environment	:
• Apply	to	continuous	control	space.
• Grid	size	is	28x28
• input	is	position	and	velocity	
which	is	float	data.	
• Output	is	2d	continuous	control	
parameters.
Comparison	about	final	distance	to	the	goal
This	result	is	from	author's	presentation
WebNav	Challenge
Environment	:
• Navigate	website	links	to	find	a	query
• Features:	average	word	embeddings
• Using	an	approximate	graph	for	planning
Evaluation:	
• Success	rate	of	within	top-4	predictions	
• Test	set	1:	start	from	index	page	
• Test	set	2:	start	from	random	page	
Result:
Conclusion
Purpose	:
• Machine	learning	based	robot	path	planning.	
Method	:	
• Learning	rewards	of	each	place	and	predict	action	
using	propagated	reward.
Result	:	
• VIN	policies	learn	an	approximate	planning	
computation	relevant	for	solving	the	task.
• Grid-worlds,	to	continuous	control,	and	even	to	
navigation	of	Wikipedia	links.
Code:
https://github.com/peisuke/vin
This	code	is	implemented	in	chainer!
Twitter:		
@peisuke
We	are	hiring	!!	
https://www.wantedly.com/companies/abeja
1 von 17

Recomendados

Reinforcement Learning : A Beginners Tutorial von
Reinforcement Learning : A Beginners TutorialReinforcement Learning : A Beginners Tutorial
Reinforcement Learning : A Beginners TutorialOmar Enayet
15.3K views37 Folien
Reinforcement learning 7313 von
Reinforcement learning 7313Reinforcement learning 7313
Reinforcement learning 7313Slideshare
13.6K views30 Folien
Reinforcement Learning von
Reinforcement LearningReinforcement Learning
Reinforcement LearningDongHyun Kwak
1.4K views61 Folien
CVIM最先端ガイド6 幾何学的推定のための最適化手法 3.5 - 3.8 von
CVIM最先端ガイド6 幾何学的推定のための最適化手法 3.5 - 3.8CVIM最先端ガイド6 幾何学的推定のための最適化手法 3.5 - 3.8
CVIM最先端ガイド6 幾何学的推定のための最適化手法 3.5 - 3.8Fujimoto Keisuke
1.5K views27 Folien
Reinforcement learning:policy gradient (part 1) von
Reinforcement learning:policy gradient (part 1)Reinforcement learning:policy gradient (part 1)
Reinforcement learning:policy gradient (part 1)Bean Yen
637 views76 Folien
Reinforcement Learning von
Reinforcement LearningReinforcement Learning
Reinforcement LearningSalem-Kabbani
934 views33 Folien

Más contenido relacionado

Was ist angesagt?

ICLR2020 オンライン読み会 Deep Semi-Supervised Anomaly Detection von
ICLR2020 オンライン読み会 Deep Semi-Supervised Anomaly DetectionICLR2020 オンライン読み会 Deep Semi-Supervised Anomaly Detection
ICLR2020 オンライン読み会 Deep Semi-Supervised Anomaly DetectionYamato OKAMOTO
1.9K views9 Folien
Reinforcement Learning 4. Dynamic Programming von
Reinforcement Learning 4. Dynamic ProgrammingReinforcement Learning 4. Dynamic Programming
Reinforcement Learning 4. Dynamic ProgrammingSeung Jae Lee
925 views19 Folien
Linear regression, costs & gradient descent von
Linear regression, costs & gradient descentLinear regression, costs & gradient descent
Linear regression, costs & gradient descentRevanth Kumar
145 views17 Folien
Introduction to Machine Learning von
Introduction to Machine LearningIntroduction to Machine Learning
Introduction to Machine LearningShahar Cohen
798 views80 Folien
An introduction to reinforcement learning von
An introduction to  reinforcement learningAn introduction to  reinforcement learning
An introduction to reinforcement learningJie-Han Chen
859 views60 Folien
深層生成モデルを用いたマルチモーダル学習 von
深層生成モデルを用いたマルチモーダル学習深層生成モデルを用いたマルチモーダル学習
深層生成モデルを用いたマルチモーダル学習Masahiro Suzuki
9.5K views23 Folien

Was ist angesagt?(20)

ICLR2020 オンライン読み会 Deep Semi-Supervised Anomaly Detection von Yamato OKAMOTO
ICLR2020 オンライン読み会 Deep Semi-Supervised Anomaly DetectionICLR2020 オンライン読み会 Deep Semi-Supervised Anomaly Detection
ICLR2020 オンライン読み会 Deep Semi-Supervised Anomaly Detection
Yamato OKAMOTO1.9K views
Reinforcement Learning 4. Dynamic Programming von Seung Jae Lee
Reinforcement Learning 4. Dynamic ProgrammingReinforcement Learning 4. Dynamic Programming
Reinforcement Learning 4. Dynamic Programming
Seung Jae Lee925 views
Linear regression, costs & gradient descent von Revanth Kumar
Linear regression, costs & gradient descentLinear regression, costs & gradient descent
Linear regression, costs & gradient descent
Revanth Kumar145 views
Introduction to Machine Learning von Shahar Cohen
Introduction to Machine LearningIntroduction to Machine Learning
Introduction to Machine Learning
Shahar Cohen798 views
An introduction to reinforcement learning von Jie-Han Chen
An introduction to  reinforcement learningAn introduction to  reinforcement learning
An introduction to reinforcement learning
Jie-Han Chen859 views
深層生成モデルを用いたマルチモーダル学習 von Masahiro Suzuki
深層生成モデルを用いたマルチモーダル学習深層生成モデルを用いたマルチモーダル学習
深層生成モデルを用いたマルチモーダル学習
Masahiro Suzuki9.5K views
Reinforcement Learning 5. Monte Carlo Methods von Seung Jae Lee
Reinforcement Learning 5. Monte Carlo MethodsReinforcement Learning 5. Monte Carlo Methods
Reinforcement Learning 5. Monte Carlo Methods
Seung Jae Lee1.7K views
Machine learning using matlab.pdf von ppvijith
Machine learning using matlab.pdfMachine learning using matlab.pdf
Machine learning using matlab.pdf
ppvijith95 views
Deep Learning - A Literature survey von Akshay Hegde
Deep Learning - A Literature surveyDeep Learning - A Literature survey
Deep Learning - A Literature survey
Akshay Hegde12.8K views
Introduction of Deep Reinforcement Learning von NAVER Engineering
Introduction of Deep Reinforcement LearningIntroduction of Deep Reinforcement Learning
Introduction of Deep Reinforcement Learning
NAVER Engineering5.3K views
Reinforcement Learning von butest
Reinforcement LearningReinforcement Learning
Reinforcement Learning
butest1.8K views
量子アニーリング解説 1 von Kohta Ishikawa
量子アニーリング解説 1量子アニーリング解説 1
量子アニーリング解説 1
Kohta Ishikawa8.1K views
MIT 6.S091: Introduction to Deep Reinforcement Learning (Deep RL) by Lex Fridman von Peerasak C.
MIT 6.S091: Introduction to Deep Reinforcement Learning (Deep RL) by Lex FridmanMIT 6.S091: Introduction to Deep Reinforcement Learning (Deep RL) by Lex Fridman
MIT 6.S091: Introduction to Deep Reinforcement Learning (Deep RL) by Lex Fridman
Peerasak C.2.2K views
Brochure TurtleBot3(A4) von ROBOTIS Japan
Brochure TurtleBot3(A4)Brochure TurtleBot3(A4)
Brochure TurtleBot3(A4)
ROBOTIS Japan23.1K views
High-Dimensional Bayesian Optimization with Constraints: Application to Powde... von Shoki Miyagawa
High-Dimensional Bayesian Optimization with Constraints: Application to Powde...High-Dimensional Bayesian Optimization with Constraints: Application to Powde...
High-Dimensional Bayesian Optimization with Constraints: Application to Powde...
Shoki Miyagawa97 views
Reinforcement learning 1.pdf von ssuserd27779
Reinforcement learning 1.pdfReinforcement learning 1.pdf
Reinforcement learning 1.pdf
ssuserd2777987 views
PR-395: Variational Image Compression with a Scale Hyperprior von Hyeongmin Lee
PR-395: Variational Image Compression with a Scale HyperpriorPR-395: Variational Image Compression with a Scale Hyperprior
PR-395: Variational Image Compression with a Scale Hyperprior
Hyeongmin Lee282 views
Multiple View Geometry - Estimation (Direct Linear Transformation) von YongHwan Baek
Multiple View Geometry - Estimation (Direct Linear Transformation)Multiple View Geometry - Estimation (Direct Linear Transformation)
Multiple View Geometry - Estimation (Direct Linear Transformation)
YongHwan Baek2.4K views
Intro to Deep Reinforcement Learning von Khaled Saleh
Intro to Deep Reinforcement LearningIntro to Deep Reinforcement Learning
Intro to Deep Reinforcement Learning
Khaled Saleh800 views

Destacado

Interaction Networks for Learning about Objects, Relations and Physics von
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 PhysicsKen Kuroki
2.2K views16 Folien
Conditional Image Generation with PixelCNN Decoders von
Conditional Image Generation with PixelCNN DecodersConditional Image Generation with PixelCNN Decoders
Conditional Image Generation with PixelCNN Decoderssuga93
5.7K views21 Folien
Fast and Probvably Seedings for k-Means von
Fast and Probvably Seedings for k-MeansFast and Probvably Seedings for k-Means
Fast and Probvably Seedings for k-MeansKimikazu Kato
1.8K views8 Folien
Dual Learning for Machine Translation (NIPS 2016) von
Dual Learning for Machine Translation (NIPS 2016)Dual Learning for Machine Translation (NIPS 2016)
Dual Learning for Machine Translation (NIPS 2016)Toru Fujino
3K views24 Folien
InfoGAN: Interpretable Representation Learning by Information Maximizing Gen... von
InfoGAN: Interpretable Representation Learning by Information Maximizing Gen...InfoGAN: Interpretable Representation Learning by Information Maximizing Gen...
InfoGAN: Interpretable Representation Learning by Information Maximizing Gen...Shuhei Yoshida
4.1K views20 Folien
Safe and Efficient Off-Policy Reinforcement Learning von
Safe and Efficient Off-Policy Reinforcement LearningSafe and Efficient Off-Policy Reinforcement Learning
Safe and Efficient Off-Policy Reinforcement Learningmooopan
3.3K views18 Folien

Destacado(18)

Interaction Networks for Learning about Objects, Relations and Physics von Ken Kuroki
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 Kuroki2.2K views
Conditional Image Generation with PixelCNN Decoders von suga93
Conditional Image Generation with PixelCNN DecodersConditional Image Generation with PixelCNN Decoders
Conditional Image Generation with PixelCNN Decoders
suga935.7K views
Fast and Probvably Seedings for k-Means von Kimikazu Kato
Fast and Probvably Seedings for k-MeansFast and Probvably Seedings for k-Means
Fast and Probvably Seedings for k-Means
Kimikazu Kato1.8K views
Dual Learning for Machine Translation (NIPS 2016) von Toru Fujino
Dual Learning for Machine Translation (NIPS 2016)Dual Learning for Machine Translation (NIPS 2016)
Dual Learning for Machine Translation (NIPS 2016)
Toru Fujino3K views
InfoGAN: Interpretable Representation Learning by Information Maximizing Gen... von Shuhei Yoshida
InfoGAN: Interpretable Representation Learning by Information Maximizing Gen...InfoGAN: Interpretable Representation Learning by Information Maximizing Gen...
InfoGAN: Interpretable Representation Learning by Information Maximizing Gen...
Shuhei Yoshida4.1K views
Safe and Efficient Off-Policy Reinforcement Learning von mooopan
Safe and Efficient Off-Policy Reinforcement LearningSafe and Efficient Off-Policy Reinforcement Learning
Safe and Efficient Off-Policy Reinforcement Learning
mooopan3.3K views
Introduction of "TrailBlazer" algorithm von Katsuki Ohto
Introduction of "TrailBlazer" algorithmIntroduction of "TrailBlazer" algorithm
Introduction of "TrailBlazer" algorithm
Katsuki Ohto1.7K views
Introduction of “Fairness in Learning: Classic and Contextual Bandits” von Kazuto Fukuchi
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 Fukuchi2.3K views
Learning to learn by gradient descent by gradient descent von Hiroyuki Fukuda
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 Fukuda2.7K views
時系列データ3 von graySpace999
時系列データ3時系列データ3
時系列データ3
graySpace9992.1K views
Improving Variational Inference with Inverse Autoregressive Flow von Tatsuya Shirakawa
Improving Variational Inference with Inverse Autoregressive FlowImproving Variational Inference with Inverse Autoregressive Flow
Improving Variational Inference with Inverse Autoregressive Flow
Tatsuya Shirakawa3.2K views
[DL輪読会]Convolutional Sequence to Sequence Learning von Deep Learning JP
[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 JP5.2K views
NIPS 2016 Overview and Deep Learning Topics von Koichi Hamada
NIPS 2016 Overview and Deep Learning Topics  NIPS 2016 Overview and Deep Learning Topics
NIPS 2016 Overview and Deep Learning Topics
Koichi Hamada14.6K views
論文紹介 Combining Model-Based and Model-Free Updates for Trajectory-Centric Rein... von Kusano Hitoshi
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 Hitoshi1.5K views
Differential privacy without sensitivity [NIPS2016読み会資料] von Kentaro Minami
Differential privacy without sensitivity [NIPS2016読み会資料]Differential privacy without sensitivity [NIPS2016読み会資料]
Differential privacy without sensitivity [NIPS2016読み会資料]
Kentaro Minami3.7K views
Matching networks for one shot learning von Kazuki Fujikawa
Matching networks for one shot learningMatching networks for one shot learning
Matching networks for one shot learning
Kazuki Fujikawa17.8K views
ICML2016読み会 概要紹介 von Kohei Hayashi
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 Hayashi4.2K views
論文紹介 Pixel Recurrent Neural Networks von Seiya Tokui
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 Tokui22.2K views

Similar a Value iteration networks

自然方策勾配法の基礎と応用 von
自然方策勾配法の基礎と応用自然方策勾配法の基礎と応用
自然方策勾配法の基礎と応用Ryo Iwaki
1.5K views76 Folien
Rapid motor adaptation for legged robots von
Rapid motor adaptation for legged robotsRapid motor adaptation for legged robots
Rapid motor adaptation for legged robotsRohit Choudhury
100 views18 Folien
Novel Graph Modeling Framework for Feature Importance Determination in Unsupe... von
Novel Graph Modeling Framework for Feature Importance Determination in Unsupe...Novel Graph Modeling Framework for Feature Importance Determination in Unsupe...
Novel Graph Modeling Framework for Feature Importance Determination in Unsupe...Neo4j
90 views51 Folien
Artificial Neural Network based Mobile Robot Navigation von
Artificial Neural Network based Mobile Robot NavigationArtificial Neural Network based Mobile Robot Navigation
Artificial Neural Network based Mobile Robot NavigationMithun Chowdhury
1.5K views28 Folien
Presentation of master thesis von
Presentation of master thesisPresentation of master thesis
Presentation of master thesisSeoung-Ho Choi
210 views31 Folien
[Paper research] GOSELO: for Robot navigation using Reactive neural networks von
[Paper research] GOSELO: for Robot navigation using Reactive neural networks[Paper research] GOSELO: for Robot navigation using Reactive neural networks
[Paper research] GOSELO: for Robot navigation using Reactive neural networksJehong Lee
48 views38 Folien

Similar a Value iteration networks(20)

自然方策勾配法の基礎と応用 von Ryo Iwaki
自然方策勾配法の基礎と応用自然方策勾配法の基礎と応用
自然方策勾配法の基礎と応用
Ryo Iwaki1.5K views
Rapid motor adaptation for legged robots von Rohit Choudhury
Rapid motor adaptation for legged robotsRapid motor adaptation for legged robots
Rapid motor adaptation for legged robots
Rohit Choudhury100 views
Novel Graph Modeling Framework for Feature Importance Determination in Unsupe... von Neo4j
Novel Graph Modeling Framework for Feature Importance Determination in Unsupe...Novel Graph Modeling Framework for Feature Importance Determination in Unsupe...
Novel Graph Modeling Framework for Feature Importance Determination in Unsupe...
Neo4j90 views
Artificial Neural Network based Mobile Robot Navigation von Mithun Chowdhury
Artificial Neural Network based Mobile Robot NavigationArtificial Neural Network based Mobile Robot Navigation
Artificial Neural Network based Mobile Robot Navigation
Mithun Chowdhury1.5K views
[Paper research] GOSELO: for Robot navigation using Reactive neural networks von Jehong Lee
[Paper research] GOSELO: for Robot navigation using Reactive neural networks[Paper research] GOSELO: for Robot navigation using Reactive neural networks
[Paper research] GOSELO: for Robot navigation using Reactive neural networks
Jehong Lee48 views
Combinatorial optimization and deep reinforcement learning von 민재 정
Combinatorial optimization and deep reinforcement learningCombinatorial optimization and deep reinforcement learning
Combinatorial optimization and deep reinforcement learning
민재 정3K views
crowd-robot interaction: crowd-aware robot navigation with attention-based DRL von 민재 정
crowd-robot interaction: crowd-aware robot navigation with attention-based DRLcrowd-robot interaction: crowd-aware robot navigation with attention-based DRL
crowd-robot interaction: crowd-aware robot navigation with attention-based DRL
민재 정315 views
Path Planning And Navigation von guest90654fd
Path Planning And NavigationPath Planning And Navigation
Path Planning And Navigation
guest90654fd4.9K views
Path Planning And Navigation von guest90654fd
Path Planning And NavigationPath Planning And Navigation
Path Planning And Navigation
guest90654fd290 views
Rahul_Kirtoniya_11800121032_CSE_Machine_Learning.pptx von RahulKirtoniya
Rahul_Kirtoniya_11800121032_CSE_Machine_Learning.pptxRahul_Kirtoniya_11800121032_CSE_Machine_Learning.pptx
Rahul_Kirtoniya_11800121032_CSE_Machine_Learning.pptx
RahulKirtoniya8 views
Analysis of Educational Robotics activities using a machine learning approach von Lorenzo Cesaretti
Analysis of Educational Robotics activities using a machine learning approachAnalysis of Educational Robotics activities using a machine learning approach
Analysis of Educational Robotics activities using a machine learning approach
Lorenzo Cesaretti161 views
Road Network Extraction using Satellite Imagery. von SUMITRAJ312049
Road Network Extraction using Satellite Imagery.Road Network Extraction using Satellite Imagery.
Road Network Extraction using Satellite Imagery.
SUMITRAJ312049260 views
Farkhatdinov Robotics education for children 2017 Accepted.pdf von MonesseKHAMISSIA1
Farkhatdinov Robotics education for children 2017 Accepted.pdfFarkhatdinov Robotics education for children 2017 Accepted.pdf
Farkhatdinov Robotics education for children 2017 Accepted.pdf
Procedural modeling using autoencoder networks von Shuhei Iitsuka
Procedural modeling using autoencoder networksProcedural modeling using autoencoder networks
Procedural modeling using autoencoder networks
Shuhei Iitsuka786 views
Autonomy Incubator Seminar Series: Tractable Robust Planning and Model Learni... von AutonomyIncubator
Autonomy Incubator Seminar Series: Tractable Robust Planning and Model Learni...Autonomy Incubator Seminar Series: Tractable Robust Planning and Model Learni...
Autonomy Incubator Seminar Series: Tractable Robust Planning and Model Learni...
AutonomyIncubator1.1K views

Más de Fujimoto Keisuke

A quantum computational approach to correspondence problems on point sets von
A quantum computational approach to correspondence problems on point setsA quantum computational approach to correspondence problems on point sets
A quantum computational approach to correspondence problems on point setsFujimoto Keisuke
1.4K views23 Folien
F0-Consistent Many-to-many Non-parallel Voice Conversion via Conditional Auto... von
F0-Consistent Many-to-many Non-parallel Voice Conversion via Conditional Auto...F0-Consistent Many-to-many Non-parallel Voice Conversion via Conditional Auto...
F0-Consistent Many-to-many Non-parallel Voice Conversion via Conditional Auto...Fujimoto Keisuke
984 views19 Folien
YOLACT real-time instance segmentation von
YOLACT real-time instance segmentationYOLACT real-time instance segmentation
YOLACT real-time instance segmentationFujimoto Keisuke
2.9K views21 Folien
Product Managerの役割、周辺ロールとの差異 von
Product Managerの役割、周辺ロールとの差異Product Managerの役割、周辺ロールとの差異
Product Managerの役割、周辺ロールとの差異Fujimoto Keisuke
1.2K views28 Folien
ChainerRLで株売買を結構頑張ってみた(後編) von
ChainerRLで株売買を結構頑張ってみた(後編)ChainerRLで株売買を結構頑張ってみた(後編)
ChainerRLで株売買を結構頑張ってみた(後編)Fujimoto Keisuke
5.6K views80 Folien
Temporal Cycle Consistency Learning von
Temporal Cycle Consistency LearningTemporal Cycle Consistency Learning
Temporal Cycle Consistency LearningFujimoto Keisuke
1.4K views19 Folien

Más de Fujimoto Keisuke(20)

A quantum computational approach to correspondence problems on point sets von Fujimoto Keisuke
A quantum computational approach to correspondence problems on point setsA quantum computational approach to correspondence problems on point sets
A quantum computational approach to correspondence problems on point sets
Fujimoto Keisuke1.4K views
F0-Consistent Many-to-many Non-parallel Voice Conversion via Conditional Auto... von Fujimoto Keisuke
F0-Consistent Many-to-many Non-parallel Voice Conversion via Conditional Auto...F0-Consistent Many-to-many Non-parallel Voice Conversion via Conditional Auto...
F0-Consistent Many-to-many Non-parallel Voice Conversion via Conditional Auto...
Fujimoto Keisuke984 views
YOLACT real-time instance segmentation von Fujimoto Keisuke
YOLACT real-time instance segmentationYOLACT real-time instance segmentation
YOLACT real-time instance segmentation
Fujimoto Keisuke2.9K views
Product Managerの役割、周辺ロールとの差異 von Fujimoto Keisuke
Product Managerの役割、周辺ロールとの差異Product Managerの役割、周辺ロールとの差異
Product Managerの役割、周辺ロールとの差異
Fujimoto Keisuke1.2K views
ChainerRLで株売買を結構頑張ってみた(後編) von Fujimoto Keisuke
ChainerRLで株売買を結構頑張ってみた(後編)ChainerRLで株売買を結構頑張ってみた(後編)
ChainerRLで株売買を結構頑張ってみた(後編)
Fujimoto Keisuke5.6K views
Temporal Cycle Consistency Learning von Fujimoto Keisuke
Temporal Cycle Consistency LearningTemporal Cycle Consistency Learning
Temporal Cycle Consistency Learning
Fujimoto Keisuke1.4K views
20190414 Point Cloud Reconstruction Survey von Fujimoto Keisuke
20190414 Point Cloud Reconstruction Survey20190414 Point Cloud Reconstruction Survey
20190414 Point Cloud Reconstruction Survey
Fujimoto Keisuke2.7K views
Sliced Wasserstein Distance for Learning Gaussian Mixture Models von Fujimoto Keisuke
Sliced Wasserstein Distance for Learning Gaussian Mixture ModelsSliced Wasserstein Distance for Learning Gaussian Mixture Models
Sliced Wasserstein Distance for Learning Gaussian Mixture Models
Fujimoto Keisuke3.7K views
LiDAR-SLAM チュートリアル資料 von Fujimoto Keisuke
LiDAR-SLAM チュートリアル資料LiDAR-SLAM チュートリアル資料
LiDAR-SLAM チュートリアル資料
Fujimoto Keisuke6.9K views
Cold-Start Reinforcement Learning with Softmax Policy Gradient von Fujimoto Keisuke
Cold-Start Reinforcement Learning with Softmax Policy GradientCold-Start Reinforcement Learning with Softmax Policy Gradient
Cold-Start Reinforcement Learning with Softmax Policy Gradient
Fujimoto Keisuke2K views
Representation learning by learning to count von Fujimoto Keisuke
Representation learning by learning to countRepresentation learning by learning to count
Representation learning by learning to count
Fujimoto Keisuke1.2K views
Dynamic Routing Between Capsules von Fujimoto Keisuke
Dynamic Routing Between CapsulesDynamic Routing Between Capsules
Dynamic Routing Between Capsules
Fujimoto Keisuke10.7K views
Deep Learning Framework Comparison on CPU von Fujimoto Keisuke
Deep Learning Framework Comparison on CPUDeep Learning Framework Comparison on CPU
Deep Learning Framework Comparison on CPU
Fujimoto Keisuke5.5K views
Global optimality in neural network training von Fujimoto Keisuke
Global optimality in neural network trainingGlobal optimality in neural network training
Global optimality in neural network training
Fujimoto Keisuke2.2K views

Último

2FA and OAuth2 in CloudStack - Andrija Panić - ShapeBlue von
2FA and OAuth2 in CloudStack - Andrija Panić - ShapeBlue2FA and OAuth2 in CloudStack - Andrija Panić - ShapeBlue
2FA and OAuth2 in CloudStack - Andrija Panić - ShapeBlueShapeBlue
31 views23 Folien
NTGapps NTG LowCode Platform von
NTGapps NTG LowCode Platform NTGapps NTG LowCode Platform
NTGapps NTG LowCode Platform Mustafa Kuğu
28 views30 Folien
ESPC 2023 - Protect and Govern your Sensitive Data with Microsoft Purview in ... von
ESPC 2023 - Protect and Govern your Sensitive Data with Microsoft Purview in ...ESPC 2023 - Protect and Govern your Sensitive Data with Microsoft Purview in ...
ESPC 2023 - Protect and Govern your Sensitive Data with Microsoft Purview in ...Jasper Oosterveld
27 views49 Folien
Automating a World-Class Technology Conference; Behind the Scenes of CiscoLive von
Automating a World-Class Technology Conference; Behind the Scenes of CiscoLiveAutomating a World-Class Technology Conference; Behind the Scenes of CiscoLive
Automating a World-Class Technology Conference; Behind the Scenes of CiscoLiveNetwork Automation Forum
43 views35 Folien
Updates on the LINSTOR Driver for CloudStack - Rene Peinthor - LINBIT von
Updates on the LINSTOR Driver for CloudStack - Rene Peinthor - LINBITUpdates on the LINSTOR Driver for CloudStack - Rene Peinthor - LINBIT
Updates on the LINSTOR Driver for CloudStack - Rene Peinthor - LINBITShapeBlue
66 views8 Folien
Data Integrity for Banking and Financial Services von
Data Integrity for Banking and Financial ServicesData Integrity for Banking and Financial Services
Data Integrity for Banking and Financial ServicesPrecisely
29 views26 Folien

Último(20)

2FA and OAuth2 in CloudStack - Andrija Panić - ShapeBlue von ShapeBlue
2FA and OAuth2 in CloudStack - Andrija Panić - ShapeBlue2FA and OAuth2 in CloudStack - Andrija Panić - ShapeBlue
2FA and OAuth2 in CloudStack - Andrija Panić - ShapeBlue
ShapeBlue31 views
NTGapps NTG LowCode Platform von Mustafa Kuğu
NTGapps NTG LowCode Platform NTGapps NTG LowCode Platform
NTGapps NTG LowCode Platform
Mustafa Kuğu28 views
ESPC 2023 - Protect and Govern your Sensitive Data with Microsoft Purview in ... von Jasper Oosterveld
ESPC 2023 - Protect and Govern your Sensitive Data with Microsoft Purview in ...ESPC 2023 - Protect and Govern your Sensitive Data with Microsoft Purview in ...
ESPC 2023 - Protect and Govern your Sensitive Data with Microsoft Purview in ...
Automating a World-Class Technology Conference; Behind the Scenes of CiscoLive von Network Automation Forum
Automating a World-Class Technology Conference; Behind the Scenes of CiscoLiveAutomating a World-Class Technology Conference; Behind the Scenes of CiscoLive
Automating a World-Class Technology Conference; Behind the Scenes of CiscoLive
Updates on the LINSTOR Driver for CloudStack - Rene Peinthor - LINBIT von ShapeBlue
Updates on the LINSTOR Driver for CloudStack - Rene Peinthor - LINBITUpdates on the LINSTOR Driver for CloudStack - Rene Peinthor - LINBIT
Updates on the LINSTOR Driver for CloudStack - Rene Peinthor - LINBIT
ShapeBlue66 views
Data Integrity for Banking and Financial Services von Precisely
Data Integrity for Banking and Financial ServicesData Integrity for Banking and Financial Services
Data Integrity for Banking and Financial Services
Precisely29 views
Migrating VMware Infra to KVM Using CloudStack - Nicolas Vazquez - ShapeBlue von ShapeBlue
Migrating VMware Infra to KVM Using CloudStack - Nicolas Vazquez - ShapeBlueMigrating VMware Infra to KVM Using CloudStack - Nicolas Vazquez - ShapeBlue
Migrating VMware Infra to KVM Using CloudStack - Nicolas Vazquez - ShapeBlue
ShapeBlue71 views
What’s New in CloudStack 4.19 - Abhishek Kumar - ShapeBlue von ShapeBlue
What’s New in CloudStack 4.19 - Abhishek Kumar - ShapeBlueWhat’s New in CloudStack 4.19 - Abhishek Kumar - ShapeBlue
What’s New in CloudStack 4.19 - Abhishek Kumar - ShapeBlue
ShapeBlue89 views
Business Analyst Series 2023 - Week 4 Session 7 von DianaGray10
Business Analyst Series 2023 -  Week 4 Session 7Business Analyst Series 2023 -  Week 4 Session 7
Business Analyst Series 2023 - Week 4 Session 7
DianaGray1042 views
CloudStack Object Storage - An Introduction - Vladimir Petrov - ShapeBlue von ShapeBlue
CloudStack Object Storage - An Introduction - Vladimir Petrov - ShapeBlueCloudStack Object Storage - An Introduction - Vladimir Petrov - ShapeBlue
CloudStack Object Storage - An Introduction - Vladimir Petrov - ShapeBlue
ShapeBlue26 views
DRaaS using Snapshot copy and destination selection (DRaaS) - Alexandre Matti... von ShapeBlue
DRaaS using Snapshot copy and destination selection (DRaaS) - Alexandre Matti...DRaaS using Snapshot copy and destination selection (DRaaS) - Alexandre Matti...
DRaaS using Snapshot copy and destination selection (DRaaS) - Alexandre Matti...
ShapeBlue26 views
iSAQB Software Architecture Gathering 2023: How Process Orchestration Increas... von Bernd Ruecker
iSAQB Software Architecture Gathering 2023: How Process Orchestration Increas...iSAQB Software Architecture Gathering 2023: How Process Orchestration Increas...
iSAQB Software Architecture Gathering 2023: How Process Orchestration Increas...
Bernd Ruecker48 views
"Surviving highload with Node.js", Andrii Shumada von Fwdays
"Surviving highload with Node.js", Andrii Shumada "Surviving highload with Node.js", Andrii Shumada
"Surviving highload with Node.js", Andrii Shumada
Fwdays33 views
KVM Security Groups Under the Hood - Wido den Hollander - Your.Online von ShapeBlue
KVM Security Groups Under the Hood - Wido den Hollander - Your.OnlineKVM Security Groups Under the Hood - Wido den Hollander - Your.Online
KVM Security Groups Under the Hood - Wido den Hollander - Your.Online
ShapeBlue75 views
Backroll, News and Demo - Pierre Charton, Matthias Dhellin, Ousmane Diarra - ... von ShapeBlue
Backroll, News and Demo - Pierre Charton, Matthias Dhellin, Ousmane Diarra - ...Backroll, News and Demo - Pierre Charton, Matthias Dhellin, Ousmane Diarra - ...
Backroll, News and Demo - Pierre Charton, Matthias Dhellin, Ousmane Diarra - ...
ShapeBlue61 views
Don’t Make A Human Do A Robot’s Job! : 6 Reasons Why AI Will Save Us & Not De... von Moses Kemibaro
Don’t Make A Human Do A Robot’s Job! : 6 Reasons Why AI Will Save Us & Not De...Don’t Make A Human Do A Robot’s Job! : 6 Reasons Why AI Will Save Us & Not De...
Don’t Make A Human Do A Robot’s Job! : 6 Reasons Why AI Will Save Us & Not De...
Moses Kemibaro27 views
PharoJS - Zürich Smalltalk Group Meetup November 2023 von Noury Bouraqadi
PharoJS - Zürich Smalltalk Group Meetup November 2023PharoJS - Zürich Smalltalk Group Meetup November 2023
PharoJS - Zürich Smalltalk Group Meetup November 2023
Noury Bouraqadi139 views

Value iteration networks