en-de
en-es
en-fr
en-pt
en-sl
en
en-zh
0.25
0.5
0.75
1.25
1.5
1.75
2
Minimax Regret of Finite Partial-Monitoring Games in Stochastic Environments
Published on Aug 02, 20113801 Views
In a partial monitoring game, the learner repeatedly chooses an action, the environment responds with an outcome, and then the learner suffers a loss and receives a feedback signal, both of which ar
Related categories
Chapter list
Minimax Regret of Finite Partial-Monitoring Games in Stochastic Environments00:00
Finite Stochastic Partial-Monitoring Games00:06
Examples01:27
Goal03:16
Previous work04:33
Our contribution06:57
Main tools 1: using L 08:14
Main tools 2: using H09:50
What makes a game easy?12:36
Algorithm outline13:54
Lower bound for hard games15:45
Discussion17:33
Thank you21:03