An Autonomous Emotional Virtual Character: An Approach with Deep and Goal-Parameterized Reinforcement Learning

Gilzamir Ferreira Gomes, Creto Augusto Vidal, Joaquim Bento Cavalcante Neto, Yuri Lenon Barbosa Nogueira
2020 Journal of Interactive Systems  
We have developed an autonomous virtual character guided by emotions. The agent is a virtual character who lives in a three-dimensional maze world. We found that emotion drivers can induce the behavior of a trained agent. Our approach is a case of goal parameterized reinforcement learning. Thus, we create conditioning between emotion drivers and a set of goals that determine the behavioral profile of a virtual character. We train agents who can randomly assume these goals while trying to
more » ... e a reward function based on intrinsic and extrinsic motivations. A mapping between motivation and emotion was carried out. So, the agent learned a behavior profile as a training goal. The developed approach was integrated with the Advantage Actor-Critic (A3C) algorithm. Experiments showed that this approach produces behaviors consistent with the objectives given to agents, and has potential for the development of believable virtual characters.
doi:10.5753/jis.2020.751 fatcat:3pmme7d2k5ebjkazsxjvgzn3qe