Presentation information

Oral presentation

General Session » [General Session] 2. Machine Learning

[1N3] [General Session] 2. Machine Learning

Tue. Jun 5, 2018 5:20 PM - 7:00 PM Room N (2F Sakurajima)

座長:松井 藤五郎(中部大学)

6:00 PM - 6:20 PM

[1N3-03] Toward satisficing in general reinforcement learning

〇Kuniaki Satori1, Yutaka Yoshida1, Kenta Yamagishi1, Yuya Ushida2, Takumi Kamiya2, Tatsuji Takahashi1 (1. Tokyo Denki University, 2. Graduate School of Tokyo Denki Univerity)

Keywords:reinforcement learning, satisficing, bounded rationality

As the scope of reinforcement learning broadens, optimization becomes less realistic, and bounded rationality that considers the limitations in agents gets more important. Satisficing, the principal model of bounded rationality, models how people and animals explore and exploit. However, there is no efficient algorithm that represents satisficing can be applied to reinforcement learning in general. We apply our satisficing model, reference satisficing (RS) value function, and the global reference conversion (GRC) technique to the broader reinforcement learning tasks than in previous studies. In the three tasks we deal with in this study, RS and GRC work well, while there are some open problems for general reinforcement learning tasks.