Open access. Graph Laplacian Based Transfer Learning Methods in Reinforcement Learning. Written By. Yi-Ting Tsao, Ke-Ting Xiao, Von-Wun Soo and Chung-Cheng ...

May 12, 2008 · 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 ...

Graph Laplacian Based Transfer Learning Methods in Reinforcement Learning.

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.

The theoretical analysis of the simple transfer method is based on the spectral analysis on graph Laplacian. Low-order basis functions of graph Laplacian ...

We present a framework for transfer in reinforcement learning based on the idea that related tasks share some common features, and that transfer can be achieved ...

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 ...

The Laplacian representation recently gains in- creasing attention for reinforcement learning as it provides succinct and informative representation for states, ...

Apr 3, 2024 · This representation is based on the graph Laplacian, which, in the tabular case, is a matrix that encodes the topology of the state space based ...

Graph Laplacian based transfer learning in reinforcement learning - The aim of transfer learning is to accelerate learning in related domains.