Sciweavers

3556 search results - page 87 / 712
» Can machine learning be secure
Sort
View
ICML
1998
IEEE
14 years 11 months ago
The MAXQ Method for Hierarchical Reinforcement Learning
This paper presents a new approach to hierarchical reinforcement learning based on the MAXQ decomposition of the value function. The MAXQ decomposition has both a procedural seman...
Thomas G. Dietterich
ICML
1998
IEEE
14 years 11 months ago
RL-TOPS: An Architecture for Modularity and Re-Use in Reinforcement Learning
This paper introduces the RL-TOPs architecture for robot learning, a hybrid system combining teleo-reactive planning and reinforcement learning techniques. The aim of this system ...
Malcolm R. K. Ryan, Mark D. Pendrith
ICML
1997
IEEE
14 years 11 months ago
Hierarchical Explanation-Based Reinforcement Learning
Explanation-Based Reinforcement Learning (EBRL) was introduced by Dietterich and Flann as a way of combining the ability of Reinforcement Learning (RL) to learn optimal plans with...
Prasad Tadepalli, Thomas G. Dietterich
ICALT
2009
IEEE
14 years 2 months ago
Supporting Teacher Intervention in Unpredictable Learning Environments
Modern teaching tools, such as educational robotics, require new learning environments. The teacher especially needs to be supported in novel ways. Conflative learning environment...
Ilkka Jormanainen, Antony Harfield, Erkki Sutinen
MLCW
2005
Springer
14 years 3 months ago
Lessons Learned in the Challenge: Making Predictions and Scoring Them
In this paper we present lessons learned in the Evaluating Predictive Uncertainty Challenge. We describe the methods we used in regression challenges, including our winning method ...
Jukka Kohonen, Jukka Suomela