[1P] G. Modeling, Hardware Implementation, and Applications

[1P-315] Short-term memory ability of reservoir-based temporal difference learning model in partially observable Markov decision process.

*Yu Yoshino¹, Yuichi Katori^1,2 (1. Future University Hakodate, 2. Institute of Industrial Science, The University of Tokyo)

Keywords:RESERVOIR COMPUTING, REINFORCEMENT LEARNING , AUTONOMOUS ROBOT