0.25
0.5
0.75
1.25
1.5
1.75
2
Multi-Objective Markov Decision Processes for Decision Support
Published on Jul 28, 20151761 Views
We present a new data analysis framework, Multi-Objective Markov Decision Processes for Decision Support, for developing sequential decision support systems. The framework extends the MultiObjective
Related categories
Chapter list
Multi-Objective MDPs for Decision Support00:00
MOMDPs for Decision Support00:08
Diagram - 101:38
Diagram - 201:58
Diagram - 302:56
Reinforcement Learning03:52
Diagram - 405:00
Decision Support Agent05:47
Defining the Reward - 108:57
Defining the Reward - 208:57
“Fitted-Q,” Briefly09:09
Non-deterministic (Set-Valued) Policies09:10
Stage 2 Decision - 109:18
Stage 2 Decision - 209:50
Q-Learning Redux10:21
Compatibility11:05
Non-Deterministic Policy11:22
Compatible Policy - 111:24
Compatible Policy - 211:41
Compatible Policy - 311:43
Q-Learning Redux: Learning Q111:45
Graph12:09
Practical Issues12:20
Non-Deterministic Policy - 413:18
“Feature Consistency”14:11
Non-Deterministic Policy - 514:59
Set-Valued Policies - 115:00
Set-Valued Policies - 215:38
MOMDPs for Decision Support (T22)15:39
Thank You16:21