A double layered state space construction method for reinforcement learning agents

In this paper, we propose a new double-layered state space construction method, which consists of Fritzke's Growing Neural Gas algorithm and a class management mechanism of GNG units. The classification algorithm yields a new class by referring to anticipation error, anticipation vectors of an originated class, and anticipation vectors GNG units belonging in the originated class.

[1]  Rolf Pfeifer,et al.  Understanding intelligence , 2020, Inequality by Design.

[2]  B Fritzke,et al.  A growing neural gas network learns topologies. G. Tesauro, DS Touretzky, and TK Leen, editors , 1995, NIPS 1995.

[3]  Patrick Reignier,et al.  Learning to categorize perceptual space of a mobile robot using fuzzy-ART neural network , 1994, Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'94).

[4]  Richard S. Sutton,et al.  Learning to predict by the methods of temporal differences , 1988, Machine Learning.

[5]  M. Asada,et al.  Action-Based State Space Construction for Robot Learning , 1997 .

[6]  Peter Dayan,et al.  Technical Note: Q-Learning , 2004, Machine Learning.