[1N1] [General Session] 2. Machine Learning

[1N1-05] Social reinforcement learning with shared reference satisficing

〇Noriaki Sonota¹, Takumi Kamiya², Yu Kono³, Tatsuji Takahashi¹ (1. School of Science and Engineering, Tokyo Denki University, 2. Graduate School of Tokyo Denki Univerity, 3. DeNA Co., Ltd.)

Keywords:social learning, bounded rationality, imitation

animals learn not only through individual trial-and-error, but also from other individuals. It is known that vertebrates cleverly utilize learning strategies such as copy-when-uncertain and copy-successful-individuals. These strategies can be applied to social reinforcement learning, although their formalizations are yet to be established. We propose a social reinforcement learning algorithm with a very narrow information sharing. The algorithm exploits RS value function that models the satisficing principle for exploration and exploitation.