MuDE: Multi-agent decomposed reward-based exploration.

In cooperative multi-agent reinforcement learning, agents jointly optimize a centralized value function based on the rewards shared by all agents and learn decentralized policies through value function decomposition. Although such a learning framework is considered effective, estimating individual contribution from the rewards, which is essential for learning highly cooperative behaviors, is difficult. In addition, it becomes more challenging when reinforcement and punishment, help in increasing or decreasing the specific behaviors of agents, coexist because the processes of maximizing reinforcement and minimizing punishment can often conflict in practice.

Association between Perceived Activity Restriction Due to People's Perception of Aging and Unmet Medical Needs among Middle-Aged and Elderly People: A Population-Based Study.

: The older members of a population might experience unmet medical needs, despite desiring medical care due to activity limitations driven by their perception of aging. This study conducted a cross-sectional analysis of the association between perceived activity restriction (PAR) due to people's own perception of aging and unmet medical needs (UMN) in late middle-aged and older Koreans based on the Korean National Health and Nutrition Examination Survey (KNHANES). : The 2016-2020 KNHANES was used to analyze a total of 2008 participants among groups aged 45 years or older by applying individual weights imposed from the raw data.