milestone Next-generation Communication Network Exploring the evolution toward 6G networks, focusing on extreme connectivity, AI-native air interfaces, and integrated non-terrestrial networks. Artificial Intelligence Artificial intelligence (AI) is the core technology for developing intelligent algorithms and systems that solve complex optimization and decision-making problems. Deep Learning Deep learning is a subset of machine learning based on artificial neural networks with multiple layers to extract higher-level features from data. Deep Reinforcement Learning Deep reinforcement learning (DRL) combines deep learning and reinforcement learning principles to enable agents to learn optimal actions in complex, dynamic environments. Multi-Agent System Multi-agent systems (MAS) study the collective behavior and coordination of multiple autonomous agents in decentralized and dynamic environments. Convex Optimization Convex optimization is a subfield of optimization focusing on minimizing convex functions over convex sets. scenario Mobile Edge Computing Mobile Edge Computing effectively brings computation and storage capabilities closer to the end user, which significantly reduces latency and enhances performance. Integrated Sensing and Communication Integrated Sensing and Communication is a key technology for 6G networks, which merges sensing and communication functionalities in a single system. Satellite Communication Satellite communication systems are key technologies for global connectivity, enabling data transmission over far distances. Drone Communication Networks Drone communication networks provide advanced wireless connectivity for aerial platforms by integrating drones as both mobile network providers and service terminals. Physical Layer Security Physical Layer Security provides an information-theoretic approach to securing wireless communication by exploiting the physical characteristics of the wireless channel. framework Single-Agent Deep Reinforcement Learning To optimize key factors of communication systems in centralized manner, we propose single-agent deep reinforcement learning framework. Multi-Agent Deep Reinforcement Learning To optimize key factors of communication systems in decentralized manner, we propose multi-agent deep reinforcement learning framework. Offline Reinforcement Learning Offline reinforcement learning enables agents to learn optimal policies from fixed, pre-collected datasets without further interaction with the environment.
