Sciweavers

ATAL
2008
Springer

Graph Laplacian based transfer learning in reinforcement learning

14 years 11 months ago
Graph Laplacian based transfer learning in reinforcement learning
The aim of transfer learning is to accelerate learning in related domains. In reinforcement learning, many different features such as a value function and a policy can be transferred from a source domain to a related target domain. Many researches focused on transfer using hand-coded translation functions that are designed by the experts a priori. However, it is not only very costly but also problem dependent. We propose to apply the Graph Laplacian that is based on the spectral graph theory to decompose the value functions of both a source domain and a target domain into a sum of the basis functions respectively. The transfer learning can be carried out by transferring weights on the basis functions of a source domain to a target domain. We investigate two types of domain transfer, scaling and topological. The results demonstrated that the transferred policy is a better prior policy to reduce the learning time. Categories and Subject Descriptors I.2.6 [Artificial Intelligence]: Learn...
Yi-Ting Tsao, Ke-Ting Xiao, Von-Wun Soo
Added 12 Oct 2010
Updated 12 Oct 2010
Type Conference
Year 2008
Where ATAL
Authors Yi-Ting Tsao, Ke-Ting Xiao, Von-Wun Soo
Comments (0)