Knowledge transfer between heterogeneous reinforcement learning agent

Journal Title: Science Paper Online - Year 2010, Vol 5, Issue 2

Abstract

Aiming at the problem of the existing knowledge transfer methods are only suitable for homogenous reinforcement learning agents, a kind of Q learning algorithm that can transfer knowledge between heterogeneous Agents with different state and action spaces. The main idea of the proposed Q learning algorithm can be described as the follows. Based on a task that was already learned by an old and a new Agent, a neural network was used to off-line learn a mapping relationship of Q value function between the two Agents. The constructed mapping of Q value function was then used to obtain Q value of the new Agent in a new task that was already learned by the old Agent while was not learned by the new Agent. The proposed Q learning algorithm can decrease the number of trials of the new Agent and so as to improve learning speed. Simulation results of 10×10 mazes illustrate the validity of the proposed Q learning algorithm.

Authors and Affiliations

Bo Liu, Ruhai Lei

Keywords

Related Articles

图像重建的分块迭代算法

图像重建重新投影(Reconstruction Re-projection)的迭代算法已在投影视野受限(Limited Field of View, LFOV)的情况下使用。视野受限情况下投影数据被截断。此处投影采用平行光束,扇形光束或锥形光束。该迭代算法对消除由于投影数据某...

Correlation of electronic structures and crystal structures with photocatalytic properties of various doped TiO2

Electronic and crystal structures of undoped, N-doped, I-doped and Pt-doped anatase TiO2 have been calculated according to density functional theory. It was found that there are some new bands in the band gap for all dop...

Research advance on chemical reaction in microchemical technology

Microchemical technology has become a very hot topic in the field of chemical industry and academy. In this paper, the feasibility of chemical reaction processes in microreactor is studied based on the application of hom...

湛江地区土壤硫沉降和氮沉降临界负荷区划

在地理信息系统支持下,用稳态法进行了湛江地区土壤的硫沉降临界负荷和氮沉降临界负荷区划。按照硫沉降临界负荷可粗略地将湛江地区划分为北部、中部和南部三部分:北部针叶林和针阔混交林地区以及南部栽培植被地区的硫沉降临界负荷较大(...

Analysis of surface stress in the thin bodies by <br /> natural boundary element method<br />

At the evaluation of surface stress in thin bodies by natural boundary element method, the nearly strongly singular integrals occurred in natural boundary integral equations when the boundary source points were close to...

Download PDF file
  • EP ID EP134251
  • DOI -
  • Views 93
  • Downloads 0

How To Cite

Bo Liu, Ruhai Lei (2010). Knowledge transfer between heterogeneous reinforcement learning agent. Science Paper Online, 5(2), 120-123. https://europub.co.uk/articles/-A-134251