论文信息 - Transfer Learning Through Graph-based Skill Acquisition

Transfer Learning Through Graph-based Skill Acquisition

Since Reinforcement Learning(RL) algorithms suffer from the curse of dimensionality in continuous domains, generalization is the most challenging issue in this area. Both skill acquisition and Transfer Learning(TL) are successful techniques to overcome such problem that result in big improvements in agent learning performance . In this paper, we propose a novel graph based skill acquisition method and a skill based transfer learning framework.

Masoud Asadpour | Farzaneh Shoeleh

[1] Hamid Beigy,et al. A novel graphical approach to automatic abstraction in reinforcement learning , 2013, Robotics Auton. Syst..

[2] Peter Stone,et al. Transfer Learning for Reinforcement Learning Domains: A Survey , 2009, J. Mach. Learn. Res..

[3] Alessandro Lazaric,et al. Transfer in Reinforcement Learning: A Framework and a Survey , 2012, Reinforcement Learning.

[4] Alireza Khadivi,et al. Automatic skill acquisition in reinforcement learning using graph centrality measures , 2012, Intell. Data Anal..

[5] Andrew G. Barto,et al. Skill Discovery in Continuous Reinforcement Learning Domains using Skill Chaining , 2009, NIPS.

[6] Parham Moradi,et al. Automatic Skill Acquisition in Reinforcement Learning Agents Using Connection Bridge Centrality , 2010, FGIT-FGCN.

[7] Andrew G. Barto,et al. Skill Characterization Based on Betweenness , 2008, NIPS.

[8] Masoud Asadpour,et al. Graph based skill acquisition and transfer Learning for continuous reinforcement learning domains , 2017, Pattern Recognit. Lett..