Dynamically providing students with clear explanations of complex spatial concepts is critical for a broad range of knowledge-based educational and training systems. This calls fo...
Stuart G. Towns, Charles B. Callaway, James C. Les...
Abstract— Groups of reinforcement learning agents interacting in a common environment often fail to learn optimal behaviors. Poor performance is particularly common in environmen...
— We adopt a form of group communication, called channeled multicast, for active rooms and other scenarios featuring strict real-time requirements, inherently unreliable communic...
We present an approach that uses Q-learning on individual robotic agents, for coordinating a missiontasked team of robots in a complex scenario. To reduce the size of the state sp...
Knowledge transfer between expert and novice agents is a challenging problem given that the knowledge representation and learning algorithms used by the novice learner can be fund...