65 search results - page 2 / 13 » Graph Laplacian based transfer learning in reinforcement lea... |
ATAL
2008
Springer
13 years 6 months ago
2008
Springer
Reinforcement Learning research is traditionally devoted to solve single-task problems. Therefore, anytime a new task is faced, learning must be restarted from scratch. Recently, ...
COLT
2006
Springer
13 years 8 months ago
2006
Springer
Abstract. The regularization functional induced by the graph Laplacian of a random neighborhood graph based on the data is adaptive in two ways. First it adapts to an underlying ma...
ICMLA
2003
13 years 6 months ago
2003
This work represents the first step towards a task library system in the reinforcement learning domain. Task libraries could be useful in speeding up the learning of new tasks th...
ICML
2007
IEEE
14 years 5 months ago
2007
IEEE
Ranking nodes in graphs is of much recent interest. Edges, via the graph Laplacian, are used to encourage local smoothness of node scores in SVM-like formulations with generalizat...
AAAI
2006
13 years 6 months ago
2006
Transfer learning concerns applying knowledge learned in one task (the source) to improve learning another related task (the target). In this paper, we use structure mapping, a ps...