This thesis investigates coordinating units through simultaneous coalition structuregeneration and task assignment in a complex Euclidean environment. The environmentused is StarCraft II, and the problem modeled and solved in the game is the distribution ofcombat units over the game’s map. The map was split into regions, and every region wasmodeled as a task to which the combat units were assigned.In a number of experiments, we compare the performance of our approach with thegame’s built-in bots. Against most of the non cheating options, our agent wins 20% of thegames played on a large map, against the Hard built-in bot. On a smaller and simpler mapit wins 22% of games played against the hardest non-cheating difficulty.One of the main limitations of the method used to solve the assignment was the utility function. Which should describe the quality of a coalition and the task assignment.However, as the utility function described the state’s utility better, the win rate increased.Therefore the result indicates that the simultaneous coalition structure generation and taskassignment work for unit distribution in a complex environment like StarCraft II if a sufficient utility function is provided.

Для решения проблемы низкой точности, слабой адаптивности и плохой интерпретируемости существующих моделей прогнозирования опасности схода грязевых потоков предлагается новый метод прогнозирования. В качестве примера рассматриваются 159 точек бедствий в бассейне реки Нуцзян в Китае. Выбраны 15 факторов влияния, и с использованием метода комбинированного взвешивания тремя сторонами проводится оценка опасности точек риска схода грязевых потоков. Затем для прогнозирования опасности схода грязевых потоков используется модель CNN-BiGRU-Attention. Для оптимизации гиперпараметров применяется улучшенный алгоритм KOA (IKOA). В конечном итоге для повышения интерпретируемости результатов прогнозирования модели введена рамка SHAP. Результаты показывают, что по сравнению с 13 текущими наиболее часто используемыми моделями прогнозирования, модель IKOA-CNN-BiGRU-Attention демонстрирует наилучшие результаты прогнозирования. / To address the issues of low accuracy, poor adaptability, and weak interpretability in existing models for predicting debris flow hazards, a new prediction method is proposed. Using 159 disaster points in the Nujiang River Basin in China as a case study, 15 influencing factors are selected, and a tripartite combined weighting method is used to evaluate the risk levels of debris flow points. Subsequently, the CNN-BiGRU-Attention model is used to predict the hazard of debris flows. The improved KOA algorithm (IKOA) is employed for hyperparameter optimization. Finally, the SHAP framework is introduced to enhance the interpretability of the model's prediction results. The results show that compared to the 13 currently commonly used prediction models, the IKOA-CNN-BiGRU-Attention model exhibits the best predictive performance.