Hoeffding and Bernstein Races for Selecting Policies in Evolutionary Direct Policy Search thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Hoeffding and Bernstein Races for Selecting Policies in Evolutionary Direct Policy Search

Published on Aug 26, 20094154 Views

Uncertainty arises in reinforcement learning from various sources, and therefore it is necessary to consider statistics based on several roll-outs for evaluating behavioral policies. We add an adaptiv