Alert button
Picture for Ryota Kanai

Ryota Kanai

Alert button

Araya Inc

Boredom-driven curious learning by Homeo-Heterostatic Value Gradients

Jun 05, 2018
Yen Yu, Acer Y. C. Chang, Ryota Kanai

Figure 1 for Boredom-driven curious learning by Homeo-Heterostatic Value Gradients
Figure 2 for Boredom-driven curious learning by Homeo-Heterostatic Value Gradients
Figure 3 for Boredom-driven curious learning by Homeo-Heterostatic Value Gradients
Figure 4 for Boredom-driven curious learning by Homeo-Heterostatic Value Gradients
Viaarxiv icon

Being curious about the answers to questions: novelty search with learned attention

Jun 01, 2018
Nicholas Guttenberg, Martin Biehl, Nathaniel Virgo, Ryota Kanai

Figure 1 for Being curious about the answers to questions: novelty search with learned attention
Figure 2 for Being curious about the answers to questions: novelty search with learned attention
Figure 3 for Being curious about the answers to questions: novelty search with learned attention
Figure 4 for Being curious about the answers to questions: novelty search with learned attention
Viaarxiv icon

Learning to generate classifiers

Mar 30, 2018
Nicholas Guttenberg, Ryota Kanai

Figure 1 for Learning to generate classifiers
Figure 2 for Learning to generate classifiers
Figure 3 for Learning to generate classifiers
Figure 4 for Learning to generate classifiers
Viaarxiv icon

Efficient Algorithms for Searching the Minimum Information Partition in Integrated Information Theory

Feb 13, 2018
Jun Kitazono, Ryota Kanai, Masafumi Oizumi

Figure 1 for Efficient Algorithms for Searching the Minimum Information Partition in Integrated Information Theory
Figure 2 for Efficient Algorithms for Searching the Minimum Information Partition in Integrated Information Theory
Figure 3 for Efficient Algorithms for Searching the Minimum Information Partition in Integrated Information Theory
Figure 4 for Efficient Algorithms for Searching the Minimum Information Partition in Integrated Information Theory
Viaarxiv icon

Curiosity-driven reinforcement learning with homeostatic regulation

Feb 07, 2018
Ildefons Magrans de Abril, Ryota Kanai

Figure 1 for Curiosity-driven reinforcement learning with homeostatic regulation
Figure 2 for Curiosity-driven reinforcement learning with homeostatic regulation
Figure 3 for Curiosity-driven reinforcement learning with homeostatic regulation
Figure 4 for Curiosity-driven reinforcement learning with homeostatic regulation
Viaarxiv icon

Learning body-affordances to simplify action spaces

Aug 15, 2017
Nicholas Guttenberg, Martin Biehl, Ryota Kanai

Figure 1 for Learning body-affordances to simplify action spaces
Figure 2 for Learning body-affordances to simplify action spaces
Figure 3 for Learning body-affordances to simplify action spaces
Figure 4 for Learning body-affordances to simplify action spaces
Viaarxiv icon

Counterfactual Control for Free from Generative Models

Mar 09, 2017
Nicholas Guttenberg, Yen Yu, Ryota Kanai

Figure 1 for Counterfactual Control for Free from Generative Models
Figure 2 for Counterfactual Control for Free from Generative Models
Figure 3 for Counterfactual Control for Free from Generative Models
Figure 4 for Counterfactual Control for Free from Generative Models
Viaarxiv icon

A description length approach to determining the number of k-means clusters

Feb 28, 2017
Hiromitsu Mizutani, Ryota Kanai

Figure 1 for A description length approach to determining the number of k-means clusters
Figure 2 for A description length approach to determining the number of k-means clusters
Figure 3 for A description length approach to determining the number of k-means clusters
Figure 4 for A description length approach to determining the number of k-means clusters
Viaarxiv icon

Permutation-equivariant neural networks applied to dynamics prediction

Dec 14, 2016
Nicholas Guttenberg, Nathaniel Virgo, Olaf Witkowski, Hidetoshi Aoki, Ryota Kanai

Figure 1 for Permutation-equivariant neural networks applied to dynamics prediction
Figure 2 for Permutation-equivariant neural networks applied to dynamics prediction
Figure 3 for Permutation-equivariant neural networks applied to dynamics prediction
Figure 4 for Permutation-equivariant neural networks applied to dynamics prediction
Viaarxiv icon

Neural Coarse-Graining: Extracting slowly-varying latent degrees of freedom with neural networks

Sep 01, 2016
Nicholas Guttenberg, Martin Biehl, Ryota Kanai

Figure 1 for Neural Coarse-Graining: Extracting slowly-varying latent degrees of freedom with neural networks
Figure 2 for Neural Coarse-Graining: Extracting slowly-varying latent degrees of freedom with neural networks
Figure 3 for Neural Coarse-Graining: Extracting slowly-varying latent degrees of freedom with neural networks
Figure 4 for Neural Coarse-Graining: Extracting slowly-varying latent degrees of freedom with neural networks
Viaarxiv icon