995 search results - page 23 / 199 » Learning Useful Horn Approximations |
SARA
2005
Springer
14 years 3 months ago
2005
Springer
Sets of features in Markov decision processes can play a critical role ximately representing value and in abstracting the state space. Selection of features is crucial to the succe...
IROS
2007
IEEE
14 years 4 months ago
2007
IEEE
: This paper presents a coarse coding technique and an action selection scheme for reinforcement learning (RL) in multi-dimensional and continuous state-action spaces following con...
PLDI
2010
ACM
14 years 2 months ago
2010
ACM
Energy-efficient computing is important in several systems ranging from embedded devices to large scale data centers. Several application domains offer the opportunity to tradeof...
QRE
2010
2010
Improving quality of prediction in highly dynamic environments using approximate dynamic programming
13 years 8 months ago
In many applications, decision making under uncertainty often involves two steps- prediction of a certain quality parameter or indicator of the system under study and the subseque...
ILP
1999
Springer
14 years 2 months ago
1999
Springer
This paper presents an application of Inductive Logic Programming (ILP) and Backpropagation Neural Network (BNN) to the problem of Thai character recognition. In such a learning pr...