69 search results - page 7 / 14 » Cross-domain transfer for reinforcement learning |
ICCBR
2009
Springer
14 years 2 months ago
2009
Springer
Positive transfer learning (TL) occurs when, after gaining experience from learning how to solve a (source) task, the same learner can exploit this experience to improve performanc...
FLAIRS
1998
13 years 9 months ago
1998
Manyindustrial processes involve makingparts with an assemblyof machines, where each machinecarries out an operation on a part, and the finished product requires a wholeseries of ...
NIPS
1997
13 years 9 months ago
1997
We present a new approach to reinforcement learning in which the policies considered by the learning process are constrained by hierarchies of partially specified machines. This ...
IJCAI
2007
13 years 9 months ago
2007
Learning capabilities of computer systems still lag far behind biological systems. One of the reasons can be seen in the inefficient re-use of control knowledge acquired over the...
IJCAI
2007
13 years 9 months ago
2007
The goal of transfer learning is to use the knowledge acquired in a set of source tasks to improve performance in a related but previously unseen target task. In this paper, we pr...