Picture for Asier Mujika

Asier Mujika

Hierarchical Attention Encoder Decoder

Add code
Jun 01, 2023
Viaarxiv icon

Online learning of long-range dependencies

Add code
May 25, 2023
Viaarxiv icon

Open-Ended Reinforcement Learning with Neural Reward Functions

Add code
Feb 16, 2022
Figure 1 for Open-Ended Reinforcement Learning with Neural Reward Functions
Figure 2 for Open-Ended Reinforcement Learning with Neural Reward Functions
Figure 3 for Open-Ended Reinforcement Learning with Neural Reward Functions
Figure 4 for Open-Ended Reinforcement Learning with Neural Reward Functions
Viaarxiv icon

Improving Gradient Estimation in Evolutionary Strategies With Past Descent Directions

Add code
Oct 11, 2019
Figure 1 for Improving Gradient Estimation in Evolutionary Strategies With Past Descent Directions
Figure 2 for Improving Gradient Estimation in Evolutionary Strategies With Past Descent Directions
Figure 3 for Improving Gradient Estimation in Evolutionary Strategies With Past Descent Directions
Figure 4 for Improving Gradient Estimation in Evolutionary Strategies With Past Descent Directions
Viaarxiv icon

Decoupling Hierarchical Recurrent Neural Networks With Locally Computable Losses

Add code
Oct 11, 2019
Figure 1 for Decoupling Hierarchical Recurrent Neural Networks With Locally Computable Losses
Figure 2 for Decoupling Hierarchical Recurrent Neural Networks With Locally Computable Losses
Figure 3 for Decoupling Hierarchical Recurrent Neural Networks With Locally Computable Losses
Figure 4 for Decoupling Hierarchical Recurrent Neural Networks With Locally Computable Losses
Viaarxiv icon

Optimal Kronecker-Sum Approximation of Real Time Recurrent Learning

Add code
Feb 11, 2019
Figure 1 for Optimal Kronecker-Sum Approximation of Real Time Recurrent Learning
Figure 2 for Optimal Kronecker-Sum Approximation of Real Time Recurrent Learning
Figure 3 for Optimal Kronecker-Sum Approximation of Real Time Recurrent Learning
Figure 4 for Optimal Kronecker-Sum Approximation of Real Time Recurrent Learning
Viaarxiv icon

The linear hidden subset problem for the EA with scheduled and adaptive mutation rates

Add code
Aug 16, 2018
Viaarxiv icon

Approximating Real-Time Recurrent Learning with Random Kronecker Factors

Add code
May 28, 2018
Figure 1 for Approximating Real-Time Recurrent Learning with Random Kronecker Factors
Figure 2 for Approximating Real-Time Recurrent Learning with Random Kronecker Factors
Figure 3 for Approximating Real-Time Recurrent Learning with Random Kronecker Factors
Figure 4 for Approximating Real-Time Recurrent Learning with Random Kronecker Factors
Viaarxiv icon

Fast-Slow Recurrent Neural Networks

Add code
Jun 09, 2017
Figure 1 for Fast-Slow Recurrent Neural Networks
Figure 2 for Fast-Slow Recurrent Neural Networks
Figure 3 for Fast-Slow Recurrent Neural Networks
Figure 4 for Fast-Slow Recurrent Neural Networks
Viaarxiv icon

Multi-task learning with deep model based reinforcement learning

Add code
May 23, 2017
Figure 1 for Multi-task learning with deep model based reinforcement learning
Figure 2 for Multi-task learning with deep model based reinforcement learning
Figure 3 for Multi-task learning with deep model based reinforcement learning
Figure 4 for Multi-task learning with deep model based reinforcement learning
Viaarxiv icon