• Electronics and Telecommunications Trends
• /
• v.34 no.6
• /
• pp.100-107
• /
• 2019

Recently, reinforcement learning (RL) has expanded from the research phase of the virtual simulation environment to a wide range of applications, such as autonomous driving, natural language processing, recommendation systems, and disease diagnosis. However, RL is less likely to be used in these complex real-world environments. In contrast, inverse reinforcement learning (IRL) can obtain optimal policies in various situations; furthermore, it can use expert demonstration data to achieve its target task. In particular, IRL is expected to be a key technology for artificial general intelligence research that can successfully perform human intellectual tasks. In this report, we briefly summarize various IRL techniques and research directions.

• KIISE Transactions on Computing Practices
• /
• v.23 no.10
• /
• pp.599-604
• /
• 2017

A useful application of smart assistants is to predict and suggest users' daily behaviors the way real assistants do. Conventional methods to predict behavior have mainly used explicit schedule information logged by a user or extracted from e-mail or SNS data. However, gathering explicit information for smart assistants has limitations, and much of a user's routine behavior is not logged in the first place. In this paper, we suggest a novel approach that combines explicit schedule information with patterns of routine behavior. We propose using inference based on a Markov decision process and learning with a reward function based on inverse reinforcement learning. The results of our experiment shows that the proposed method outperforms comparable models on a life-log dataset collected over six weeks.

• Journal of the Korea Society for Simulation
• /
• v.30 no.1
• /
• pp.139-152
• /
• 2021

Simulations enable virtually experiencing rare events as well as analytically analyzing such events. Defense modeling and simulation research and develops the virtual and the constructive simulations to support these utilizations. These virtual and constructive(VC) simulations can interoperate to simultaneously virtual combat experience as well as evaluations on tactics and intelligence of combat entities. Moreover, recently, for artificial intelligence researches, it is necessary to retrieve human behavior data to proceed the imitation learning and the inverse reinforcement learning. The presented work illustrates a case study of VC interoperations in the aircombat scenario, and the work analyze the collected human behavior data from the VC interoperations. Through this case study, we discuss how to build the VC simulation in the aircombat area and how to utilize the collected human behavior data.