Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Ryota Kanai

Experimental Evidence that Empowerment May Drive Exploration in Sparse-Reward Environments


Jul 14, 2021
Francesco Massari, Martin Biehl, Lisa Meeden, Ryota Kanai

* 6 pages, 3 figures, to be published in proceedings of the International Conference on Development and Learning 2021 

  Access Paper or Ask Questions

Deep Learning and the Global Workspace Theory


Dec 04, 2020
Rufin VanRullen, Ryota Kanai


  Access Paper or Ask Questions

Non-trivial informational closure of a Bayesian hyperparameter


Oct 05, 2020
Martin Biehl, Ryota Kanai


  Access Paper or Ask Questions

A unified strategy for implementing curiosity and empowerment driven reinforcement learning


Jun 18, 2018
Ildefons Magrans de Abril, Ryota Kanai

* 13 pages, 8 figures 

  Access Paper or Ask Questions

Boredom-driven curious learning by Homeo-Heterostatic Value Gradients


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

* 21 pages, 4 figures 

  Access Paper or Ask Questions

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


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

* 8 pages, 7 figures, ALife 2018 

  Access Paper or Ask Questions

Learning to generate classifiers


Mar 30, 2018
Nicholas Guttenberg, Ryota Kanai

* 11 pages, 3 figures 

  Access Paper or Ask Questions

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


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


  Access Paper or Ask Questions

Curiosity-driven reinforcement learning with homeostatic regulation


Feb 07, 2018
Ildefons Magrans de Abril, Ryota Kanai

* Presented at the NIPS 2017 Workshop: Cognitively Informed Artificial Intelligence: Insights From Natural Intelligence 

  Access Paper or Ask Questions

Learning body-affordances to simplify action spaces


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

* 4 pages, 4 figures 

  Access Paper or Ask Questions

Counterfactual Control for Free from Generative Models


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

* 6 pages, 5 figures 

  Access Paper or Ask Questions

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


Feb 28, 2017
Hiromitsu Mizutani, Ryota Kanai

* 27 pages, 6 figures 

  Access Paper or Ask Questions

Permutation-equivariant neural networks applied to dynamics prediction


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

* 7 pages, 4 figures 

  Access Paper or Ask Questions

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


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

* 9 pages, 5 figures, 3 tables 

  Access Paper or Ask Questions