—Multi-robot reinforcement learning is a very challenging area due to several issues, such as large state spaces, difficulty in reward assignment, nondeterministic action selecti...
In this paper, we investigate the hypothesis that plan recognition can significantly improve the performance of a casebased reinforcement learner in an adversarial action selectio...
In this paper we describe MRSCL Geometry a collaborative educational activity that explores the use of robotic technology and wirelessly connected Pocket PCs as tools for teaching ...
We present new algorithms for inverse optimal control (or inverse reinforcement learning, IRL) within the framework of linearlysolvable MDPs (LMDPs). Unlike most prior IRL algorit...
Agents (hardware or software) that act autonomously in an environment have to be able to integrate three basic behaviors: planning, execution, and learning. This integration is man...