Picture for Michael Fairbank

Michael Fairbank

Deep Learning in Target Space

Add code
Jun 02, 2020
Figure 1 for Deep Learning in Target Space
Figure 2 for Deep Learning in Target Space
Figure 3 for Deep Learning in Target Space
Figure 4 for Deep Learning in Target Space
Viaarxiv icon

Optimal resampling for the noisy OneMax problem

Add code
Jun 12, 2017
Figure 1 for Optimal resampling for the noisy OneMax problem
Figure 2 for Optimal resampling for the noisy OneMax problem
Figure 3 for Optimal resampling for the noisy OneMax problem
Figure 4 for Optimal resampling for the noisy OneMax problem
Viaarxiv icon

The Importance of Clipping in Neurocontrol by Direct Gradient Descent on the Cost-to-Go Function and in Adaptive Dynamic Programming

Add code
Feb 22, 2013
Figure 1 for The Importance of Clipping in Neurocontrol by Direct Gradient Descent on the Cost-to-Go Function and in Adaptive Dynamic Programming
Figure 2 for The Importance of Clipping in Neurocontrol by Direct Gradient Descent on the Cost-to-Go Function and in Adaptive Dynamic Programming
Figure 3 for The Importance of Clipping in Neurocontrol by Direct Gradient Descent on the Cost-to-Go Function and in Adaptive Dynamic Programming
Figure 4 for The Importance of Clipping in Neurocontrol by Direct Gradient Descent on the Cost-to-Go Function and in Adaptive Dynamic Programming
Viaarxiv icon

The Divergence of Reinforcement Learning Algorithms with Value-Iteration and Function Approximation

Add code
Jul 29, 2012
Viaarxiv icon

The Local Optimality of Reinforcement Learning by Value Gradients, and its Relationship to Policy Gradient Learning

Add code
Jan 02, 2011
Viaarxiv icon

Reinforcement Learning by Value Gradients

Add code
Mar 25, 2008
Figure 1 for Reinforcement Learning by Value Gradients
Figure 2 for Reinforcement Learning by Value Gradients
Figure 3 for Reinforcement Learning by Value Gradients
Figure 4 for Reinforcement Learning by Value Gradients
Viaarxiv icon