开课单位--麦吉尔大学
11
12
13
14
15
16
17
18
19
20
![](functions/showpic.php?filename=2016111009123881.png)
![](functions/showpic.php?filename=2016112207333066.png)
Probabilistic Decision-Making Under Model Uncertainty[不确定性条件下模型的概率决策]
Joelle Pineau(麦吉尔大学) Partially Observable Markov Decision Processes offer a rich mathematical framework for decision-making under uncertainty. In recent years, a number of...
热度:38
Joelle Pineau(麦吉尔大学) Partially Observable Markov Decision Processes offer a rich mathematical framework for decision-making under uncertainty. In recent years, a number of...
热度:38
![](functions/showpic.php?filename=2016112304015670.png)
Temporal Motifs Reveal the Dynamics of Editor Interactions in Wikipedia[时间主题揭示维基百科编辑互动的动态]
David Jurgens(麦吉尔大学) Wikipedia is a collaborative setting with both combative and cooperative editing. We propose a new method for investigating the types of editor intera...
热度:67
David Jurgens(麦吉尔大学) Wikipedia is a collaborative setting with both combative and cooperative editing. We propose a new method for investigating the types of editor intera...
热度:67
![](functions/showpic.php?filename=2016112902510324.png)
Reinforcement Learning in the Presence of Rare Events[在罕见事件的存在下强化学习]
Jordan Frank(麦吉尔大学) We consider the task of reinforcement learning in an environment in which rare significant events occur independently of the actions selected by the c...
热度:43
Jordan Frank(麦吉尔大学) We consider the task of reinforcement learning in an environment in which rare significant events occur independently of the actions selected by the c...
热度:43
![](functions/showpic.php?filename=2016123111354995.png)
Management Education Responses to Global Crisis: Challenges and Opportunities[管理教育应对全球危机:挑战与机遇]
Nancy Adler(麦吉尔大学)
热度:33
Nancy Adler(麦吉尔大学)
热度:33
![](functions/showpic.php?filename=2018020305143639.jpg)
![](functions/showpic.php?filename=2019091608272767.jpg)
Active Learning in Network Monitoring[网络监控中的主动学习]
Mark Coates(麦吉尔大学) In several latency in obtaining information about the state of the network. The adoption of active learning techniques can result in a dramatic reduct...
热度:38
Mark Coates(麦吉尔大学) In several latency in obtaining information about the state of the network. The adoption of active learning techniques can result in a dramatic reduct...
热度:38
![](functions/showpic.php?filename=2019042508094953.png)
Piecewise-Stationary Bandit Problems with Side Observations[具有侧面观测的分段 - 平稳强盗问题]
Jia Yuan Yu(麦吉尔大学) We consider a sequential decision problem where the rewards are generated by a piecewise-stationary distribution. However, the different reward distri...
热度:31
Jia Yuan Yu(麦吉尔大学) We consider a sequential decision problem where the rewards are generated by a piecewise-stationary distribution. However, the different reward distri...
热度:31
![](functions/showpic.php?filename=2019042409350318.png)
Piecewise-Stationary Bandit Problems with Side Information[边信息的分段 - 平稳强盗问题]
Jia Yuan Yu(麦吉尔大学) We consider a sequential decision problem where the rewards are generated by a piecewise-stationary distribution. However, the different reward distri...
热度:28
Jia Yuan Yu(麦吉尔大学) We consider a sequential decision problem where the rewards are generated by a piecewise-stationary distribution. However, the different reward distri...
热度:28
![](functions/showpic.php?filename=2019042405084011.png)
Welcome to the Multidisciplinary Symposium on Reinforcement Learning[欢迎参加关于加强学习的多学科研讨会]
Doina Precup(麦吉尔大学) In the last 25 years, reinforcement learning research has made great strides and has had a significant impact within several fields, including * ...
热度:28
Doina Precup(麦吉尔大学) In the last 25 years, reinforcement learning research has made great strides and has had a significant impact within several fields, including * ...
热度:28