Considering Unseen States as Impossible in Factored Reinforcement Learning thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Considering Unseen States as Impossible in Factored Reinforcement Learning

Published on Oct 20, 20092773 Views

The Factored Markov Decision Process (FMDP) framework is a standard representation for sequential decision problems under uncertainty where the state is represented as a collection of random variables