开课单位--阿尔伯塔大学
21
22
23
24
25
26
27
28
29
30
![](functions/showpic.php?filename=2019072603095371.png)
Improved Algorithms for Linear Stochastic Bandits[线性随机带的改进算法]
Yasin Abbasi-Yadkori(阿尔伯塔大学) We improve the theoretical analysis and empirical performance of algorithms for the stochastic multi-armed bandit problem and the linear stochastic mu...
热度:104
Yasin Abbasi-Yadkori(阿尔伯塔大学) We improve the theoretical analysis and empirical performance of algorithms for the stochastic multi-armed bandit problem and the linear stochastic mu...
热度:104
![](functions/showpic.php?filename=2019071702520876.jpg)
Introduction to Reinforcement Learning[强化学习简介]
Csaba Szepesvári(阿尔伯塔大学) The tutorial will introduce Reinforcement Learning, that is, learning what actions to take, and when to take them, so as to optimize long-term per...
热度:92
Csaba Szepesvári(阿尔伯塔大学) The tutorial will introduce Reinforcement Learning, that is, learning what actions to take, and when to take them, so as to optimize long-term per...
热度:92
![](functions/showpic.php?filename=2019070209414191.jpg)
Efficient Discriminative Training Method for Structured Predictions[结构预测的有效判别训练方法]
Huizhen Yu(阿尔伯塔大学) We propose an efficient discriminative training method for generative models under supervised learning. In our setting, fully observed instances are g...
热度:53
Huizhen Yu(阿尔伯塔大学) We propose an efficient discriminative training method for generative models under supervised learning. In our setting, fully observed instances are g...
热度:53
![](functions/showpic.php?filename=2019063008305247.png)
RL Glue and Codecs Glue[RL胶水和编解码胶水]
Brian Tanner(阿尔伯塔大学) RL-Glue is a protocol and software implementation for evaluating reinforcement learning algorithms. Our system facilitates the comparison of alternati...
热度:33
Brian Tanner(阿尔伯塔大学) RL-Glue is a protocol and software implementation for evaluating reinforcement learning algorithms. Our system facilitates the comparison of alternati...
热度:33
![](functions/showpic.php?filename=2019030708204212.png)
Agnostic KWIK learning and efficient approximate reinforcement learning[不可知的KWIK学习和有效的近似强化学习]
Csaba Szepesvári(阿尔伯塔大学) A popular approach in reinforcement learning is to use a model-based algorithm, i.e., an algorithm that utilizes a model learner to learn an approxima...
热度:55
Csaba Szepesvári(阿尔伯塔大学) A popular approach in reinforcement learning is to use a model-based algorithm, i.e., an algorithm that utilizes a model learner to learn an approxima...
热度:55
![](functions/showpic.php?filename=2019051005542882.png)
SIGKDD Explorations Newsletter Report[Sigkdd探索新闻稿报告]
Osmar R. Zaïane(阿尔伯塔大学) Explorations is published twice yearly, in June/July and in December/January each year. The newsletter is distributed in hardcopy form to all members ...
热度:212
Osmar R. Zaïane(阿尔伯塔大学) Explorations is published twice yearly, in June/July and in December/January each year. The newsletter is distributed in hardcopy form to all members ...
热度:212
![](functions/showpic.php?filename=2019050501551999.png)
Identfying Potentiallcy Important Conepts and Relations in an Ontology[本体论中重要概念与关系的识别 ]
Gang Wu(阿尔伯塔大学 ) More and more ontologies have been published and used widely on the web. In order to make good use of an ontology, especially a new and complex ontolo...
热度:35
Gang Wu(阿尔伯塔大学 ) More and more ontologies have been published and used widely on the web. In order to make good use of an ontology, especially a new and complex ontolo...
热度:35
![](functions/showpic.php?filename=2019042702195795.png)
Extracting Meta Statements from the Blogosphere[从博客圈中提取元语句]
Filipe Mesquita(阿尔伯塔大学) Information extraction systems have been recently proposed for organizing and exploring content in large online text corpora as information networks. ...
热度:26
Filipe Mesquita(阿尔伯塔大学) Information extraction systems have been recently proposed for organizing and exploring content in large online text corpora as information networks. ...
热度:26
![](functions/showpic.php?filename=2019042409212569.png)
Optimal Reverse Prediction: A Unified Perspective on Supervised, Unsupervised and Semi-Supervised Learning[最优逆向预测:监督,无监督和半监督学习的统一视角]
Linli Xu(阿尔伯塔大学) raining principles for unsupervised learning are often derived from motivations that appear to be independent of supervised learning, causing a prolif...
热度:32
Linli Xu(阿尔伯塔大学) raining principles for unsupervised learning are often derived from motivations that appear to be independent of supervised learning, causing a prolif...
热度:32
![](functions/showpic.php?filename=2019042407391336.png)
Fast Gradient-Descent Methods for Temporal-Difference Learning with Linear Function Approximation[线性函数逼近的时差学习快速梯度下降法]
Richard S. Sutton(阿尔伯塔大学) Sutton, Szepesvari and Maei (2009) recently introduced the first temporal-difference learning algorithm compatible with both linear function approxima...
热度:83
Richard S. Sutton(阿尔伯塔大学) Sutton, Szepesvari and Maei (2009) recently introduced the first temporal-difference learning algorithm compatible with both linear function approxima...
热度:83