0.25
0.5
0.75
1.25
1.5
1.75
2
Learning Nash Equilibrium for General-Sum Markov Games from Batch Dat
Published on Aug 23, 20162027 Views
Related categories
Chapter list
Learning Nash Equilibrium for General-Sum Markov Games from Batch Data00:00
Motivation - 100:12
Motivation - 200:46
Motivation - 301:11
Motivation - 401:48
Motivation - 502:09
Motivation - 602:49
Motivation - 703:51
Motivation - 804:14
Motivation - 904:29
Motivation - 1004:39
Motivation - 1105:00
Previous Work & Contributions05:24
Contributions07:04
Framework07:27
The Batch Scenario08:16
Q-functions08:51
Best Response09:34
Nash equilibrium, weak ε-Nash equilibrium10:09
Bellman Residual Approach10:45
What can we guarantee?12:14
Estimators13:00
Learning Process and Experiment - 113:23
Learning Process and Experiment - 214:03
Conclusion14:54