FRAC-Q-Learning: A Reinforcement Learning with Boredom Avoidance Processes for Social Robots

arXiv:2311.15327v3 Announce Type: replace-cross
Abstract: The reinforcement learning algorithms have often been applied to social robots. However, most reinforcement learning algorithms were not optimized for the use of social robots, and consequently they may bore users. We proposed a new reinforcement learning method specialized for the social robot, the FRAC-Q-learning, that can avoid user boredom. The proposed algorithm consists of a forgetting process in addition to randomizing and categorizing processes. This study evaluated interest and boredom hardness scores of the …

abstract algorithms arxiv cs.hc cs.lg cs.ro however processes q-learning reinforcement reinforcement learning robot robots social type