Decision-making plays an essential role in various real-world systems like automatic driving, traffic dispatching, information system management, and emergency command and control. Recent breakthroughs in computer game scenarios using deep reinforcement learning for intelligent decision-making have paved decision-making intelligence as a burgeoning research direction. In complex practical systems, however, factors like coupled distracting features, long-term interact links, and adversarial environments and opponents, make decision-making in practical applications challenging in modeling, computing, and explaining. This work proposes game interactive learning, a novel paradigm as a new approach towards intelligent decision-making in complex and adversarial environments. This novel paradigm highlights the function and role of a human in the process of intelligent decision-making in complex systems. It formalizes a new learning paradigm for exchanging information and knowledge between humans and the machine system. The proposed paradigm first inherits methods in game theory to model the agents and their preferences in the complex decision-making process. It then optimizes the learning objectives from equilibrium analysis using reformed machine learning algorithms to compute and pursue promising decision results for practice. Human interactions are involved when the learning process needs guidance from additional knowledge and instructions, or the human wants to understand the learning machine better. We perform preliminary experimental verification of the proposed paradigm on two challenging decision-making tasks in tactical-level War-game scenarios. Experimental results demonstrate the effectiveness of the proposed learning paradigm.

Context-awareness enhances human-centric, intelligent behavior in a smart environment; however, context-awareness is not widely used due to the lack of effective infrastructure to support context-aware applications. This paper presents an agent-based middleware for providing context-aware services for smart spaces to afford effective support for context acquisition, representation, interpretation, and utilization to applications. The middleware uses a formal context model, which combines first order probabilistic logic (FOPL) and web ontology language (OWL) ontologies, to provide a common understanding of contextual information to facilitate context modeling and reasoning about imperfect and ambiguous contextual information and to enable context knowledge sharing and reuse. A context inference mechanism based on an extended Bayesian network approach is used to enable automated reactive and deductive reasoning. The middleware is used in a case study in a smart classroom, and performance evaluation result shows that the context reasoning algorithm is good for non-time-critical applications and that the complexity is highly sensitive to the size of the context dataset.