Abstract. We consider batch reinforcement learning problems in continuous space, expected total discounted-reward Markovian Decision Problems. As opposed to previous theoretical wo...
: Awareness is required for supporting all forms of cooperation. In Computer Supported Collaborative Learning (CSCL), awareness can be used for enhancing collaborative opportunitie...
When the transition probabilities and rewards of a Markov Decision Process are specified exactly, the problem can be solved without any interaction with the environment. When no s...
The paper addresses the purposes and design decisions produced while developing a peer-to-peer virtual world platform. The work is being done within the FP7 VirtualLife project. Th...
This paper summarizes results from two educational research Ph.D. theses carried out in recent years at the "Laboratoire de Robotique Pédagogique" of the Université de...