— In the reinforcement learning literature, transfer is the capability to reuse on a new problem what has been learnt from previous experiences on similar problems. Adapting tran...
The paper explores a very simple agent design method called Q-decomposition, wherein a complex agent is built from simpler subagents. Each subagent has its own reward function and...
Factored representations, model-based learning, and hierarchies are well-studied techniques for improving the learning efficiency of reinforcement-learning algorithms in large-sca...
Carlos Diuk, Alexander L. Strehl, Michael L. Littm...
AbstractGroup utility functions are an extension of the common team utility function for providing multiple agents with a common reinforcement learning signal for learning cooperat...
Abstract information refers to information that a user can’t directly obtain just by visualizing the spatial information of objects in a 3D virtual environment (3DVE). This thesi...