Fast Gradient-Descent Methods for Temporal-Difference Learning with Linear Function Approximation thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Fast Gradient-Descent Methods for Temporal-Difference Learning with Linear Function Approximation

Published on Sep 17, 20097446 Views

Sutton, Szepesvari and Maei (2009) recently introduced the first temporal-difference learning algorithm compatible with both linear function approximation and off-policy training, and whose complexity

Related categories