JSAI2021
Jun 8 - Jun 30, 2021Online
JSAI2021
Jun 8 - Jun 30, 2021Online
[1G2-GS-2a-05]The effect of shared global aspiration and GRC in social reinforcement learning
〇Takumi Akiba1, Tatsuji Takahashi2, Daisuke Uragami1(1. Nihon University, 2. Tokyo Denki University)
Keywords:
Reinforcement learning,Satisficing,Shared global aspiration
The goal of “social reinforcement learning” would be to realize effective learning by introducing the social nature of
humans and organisms, into the framework of reinforcement learning. The social nature includes sharing information with others. The purpose of this study is to reveal the effect of sharing the maximum value of profit as a global aspiration and converting it to the aspiration value of each state in the framework of social reinforcement learning. The results show that the policy that combines the above two mechanisms is more adaptable to the two important factors of the number of agents and reward setting, compared to the policy that shares the action value and aspiration value of all states. It suggests that the sparseness of the information sharing and the resulting diversity in each agent contributes to the optimal performance.
humans and organisms, into the framework of reinforcement learning. The social nature includes sharing information with others. The purpose of this study is to reveal the effect of sharing the maximum value of profit as a global aspiration and converting it to the aspiration value of each state in the framework of social reinforcement learning. The results show that the policy that combines the above two mechanisms is more adaptable to the two important factors of the number of agents and reward setting, compared to the policy that shares the action value and aspiration value of all states. It suggests that the sparseness of the information sharing and the resulting diversity in each agent contributes to the optimal performance.