
Experimental Evidence that Empowerment May Drive Exploration in SparseReward Environments
Reinforcement Learning (RL) is known to be often unsuccessful in environ...
read it

Deep Learning and the Global Workspace Theory
Recent advances in deep learning have allowed Artificial Intelligence (A...
read it

Nontrivial informational closure of a Bayesian hyperparameter
We investigate the nontrivial informational closure (NTIC) of a Bayesia...
read it

A unified strategy for implementing curiosity and empowerment driven reinforcement learning
Although there are many approaches to implement intrinsically motivated ...
read it

Boredomdriven curious learning by HomeoHeterostatic Value Gradients
This paper presents the HomeoHeterostatic Value Gradients (HHVG) algori...
read it

Being curious about the answers to questions: novelty search with learned attention
We investigate the use of attentional neural network layers in order to ...
read it

Learning to generate classifiers
We train a network to generate mappings between training sets and classi...
read it

Curiositydriven reinforcement learning with homeostatic regulation
We propose a curiosity reward based on information theory principles and...
read it

Efficient Algorithms for Searching the Minimum Information Partition in Integrated Information Theory
The ability to integrate information in the brain is considered to be an...
read it

Learning bodyaffordances to simplify action spaces
Controlling embodied agents with many actuated degrees of freedom is a c...
read it

A description length approach to determining the number of kmeans clusters
We present an asymptotic criterion to determine the optimal number of cl...
read it

Counterfactual Control for Free from Generative Models
We introduce a method by which a generative model learning the joint dis...
read it

Permutationequivariant neural networks applied to dynamics prediction
The introduction of convolutional layers greatly advanced the performanc...
read it

Neural CoarseGraining: Extracting slowlyvarying latent degrees of freedom with neural networks
We present a loss function for neural networks that encompasses an idea ...
read it
Ryota Kanai
is this you? claim profile