<ul><li>Assignment problems are combinatorial optimization problems where agents need to be assigned to tasks while maximizing utility and satisfying constraints.</li><li>Multi-agent reinforcement learning (MARL) is applied to solve assignment problems that unfold over time.</li><li>The algorithm uses bootstrapping from a polynomial-time greedy solver and further experience to learn the value of assignments.</li><li>The distributed optimal assignment mechanism is employed to choose assignments.</li></ul>

Multi Agent Reinforcement Learning for Sequential Satellite Assignment Problems

Discover more