Recharging Bandits
1 509
55.9
Microsoft Research320 тыс
Следующее
10.04.18 – 1 28840:11Популярные
83 дня – 6145:18
119 дней – 10 75612:33Опубликовано 10 апреля 2018, 18:36
We introduce a general model of bandit problems in which the expected payout of an arm is an increasing concave function of the time since it was last played. We first develop approximation algorithms for the underlying optimization problem of determining a reward-maximizing sequence of arm pulls. We then show how to use these algorithms in a learning setting to obtain sublinear regret.
See more at microsoft.com/en-us/research/v...
See more at microsoft.com/en-us/research/v...
Свежие видео
14 часов – 3761:48
19 часов – 1 5124:52
4 дня – 8622:42
5 дней – 4759:49
Случайные видео
90 дней – 12 5939:52
06.09.22 – 1 0392:25
20.11.21 – 8 19957:55
05.10.21 – 634 9494:47
14.07.21 – 3 8720:49
14.11.12 – 65 3213:18
1 день – 1 2202:21
1 день – 1441:04:15
6 дней – 1 7179:10
12 дней – 18 76813:35
15 дней – 151 50415:22
15 дней – 6 5070:09