video thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

A Semi-parametric Statistical Approach to Model-free Policy Evaluation

Published on Feb 4, 20252992 Views

Reinforcement learning (RL) methods based on least-squares temporal difference (LSTD) have been developed recently and have shown good practical performance. However, the quality of their estimation h

Presentation