搜索结果: 1-1 共查到“数理逻辑与数学基础 Multi-Armed Bandit”相关记录1条 . 查询时间(0.137 秒)
Learning in A Changing World: Non-Bayesian Restless Multi-Armed Bandit
Non-Bayesian Multi-Armed Bandit
font style='font-size:12px;'>
2010/11/24
We consider the restless multi-armed bandit (RMAB) problem with unknown dynamics. In this problem, at each time, a player chooses K out of N (N > K) arms to play. The state of each arm determines the ...