[3P] G. Modeling, Hardware Implementation, and Applications

[3P-261] Decision uniqueness and experience saturation define the appropriateness of state expansion: comparison between dynamic state space reinforcement learning model and Dirichlet models

*Kazuhiro Sakamoto^1,2, Tokio Katakura², Hajime Mushiake² (1. Fac Med, Tohoku Med Pharm Univ, Sendai, Japan, 2. Grad Sch Med, Tohoku Univ, Sendai, Japan)

Keywords:reinforcement learning, dynamic state space, decision uniqueness, experience saturation