[1G2-GS-2a] 機械学習：強化学習

[1G2-GS-2a-04] Simulation study of Stochastic Risk-sensitive Satisificing policy which is based on non-satisfaction equilibrium

〇Toshikatsu Kato¹, Yu Kohno², Tatsuji Takahashi² (1. Graduate School of Tokyo Denki University, 2. School of Science and Engineering, Tokyo Denki University)

Keywords:Reinforcement learning, Machine learning, Bandit Problem, Satisficing

We humans tend to search for a satisfiable action above an acceptability threshold (satisficing). A value function that implements satisficing together with the prospect theory-like risk attitudes called “risk-sensitive satisficing” (RS) model shows superior results in the bandit problems. However, wider application and analysis of the behavior of the model is intractable in some ways, because of the deterministic nature of the policy. In this study, we introduce the stochastic version of RS (SRS). Through comparison of RS and SRS in stationary and non-stationary environments, we show the merits of SRS.