Perkembangan Perilaku Pembelajaran Peserta Didik dengan Menggunakan Partially Observable Markov Decision Processes

The School Community can be considered as an agent in a multi-agent system because there is dynamic interaction in a school system. The important thing in a multi-agent system is managing relationships between agents to achieve coordinated behavior by developing knowledge, attitudes and practices, namely the factors that shape environmental behavior. This research extends the framework of partially observable Markov decision processes (POMDPs) to multi-agent settings by incorporating the idea of ​​agent models into the state space. The results of this research show that (POMDP) ​​is effective for understanding and managing learning behavior in schools.