We have been developing Rogue, an architecture that integrates high-level planning with a low-level executing robotic agent. Rogue is designed as the oce gofer task planner for X...
Programming robots to carry out useful tasks is both a complex and non-trivial exercise. A simple and intuitive method to allow humans to train and shape robot behaviour is clearl...
Joe Saunders, Chrystopher L. Nehaniv, Kerstin Daut...
In this paper, we investigate the use of hierarchical reinforcement learning (HRL) to speed up the acquisition of cooperative multi-agent tasks. We introduce a hierarchical multi-a...
Rajbala Makar, Sridhar Mahadevan, Mohammad Ghavamz...
An important issue in reinforcement learning is how to incorporate expert knowledge in a principled manner, especially as we scale up to real-world tasks. In this paper, we presen...
Eric Wiewiora, Garrison W. Cottrell, Charles Elkan
A central problem in artificial intelligence is to choose actions to maximize reward in a partially observable, uncertain environment. To do so, we must learn an accurate model of ...