Towards learning agents with personality traits: Modeling Openness to Experience. (June 2019)

• Record Type: Journal Article
• Authors: Ramicic, Mirza; Bonarini, Andrea
• Is Part Of: Cognitive systems research. Volume 55(2019)
• Page Start: 124
• Page End: 134
• Publication Date: 2019-06
• Subjects: Reinforcement learning -- Intelligent agents -- Neural networks -- Cognitive architecture -- Personality traits; Cognition -- Periodicals; Cognitive engineering (System design) -- Periodicals; Artificial intelligence -- Periodicals; 153.05
• DOI: 10.1016/j.cogsys.2019.01.006
• Languages: English
• ISSNs: 1389-0417

Abstract

Abstract: Recent advances in neurosciences and cognitive sciences show us that the human neocortex is not a slave to the experiences from our perception and that the memories stored in hippocampus are goal weighted during the replay of the experiences for the purpose of re-learning from them. Temporal difference reinforcement learning systems that use neural networks as function approximators rely on an experience replay memory structure similar to the hippocampus. We bring forward this similarity and present a novel way of using a goal weighted prioritization of the memory that is biologically inspired. Furthermore, we introduce a novel prioritization criteria called Variety of Experience Index, or VEI, for weighting the selection of the experiences that are stored in the replay memory. Weighting the experiences based on two different extremes of VEI can behaviourally modify the agent's learning process, generating different types of learning agents that exhibit different personality traits along the dimension of Openness to Experience.