A gradient-based method for both symmetric and asymmetric multiagent reinforcement learning is introduced in this paper. Symmetric multiagent reinforcement learning addresses the ...
— We present a framework for composing motor controllers into autonomous composite reactive behaviors for bipedal robots and autonomous, physically-simulated humanoids. A key con...
Petros Faloutsos, Michiel van de Panne, Demetri Te...
We study on-line play of repeated matrix games in which the observations of past actions of the other player and the obtained reward are partial and stochastic. We define the Part...
This paper offers a fresh perspective to study the role and implications of information and communications technologies (ICT) in processes of local democracy. It moves away from ea...
The potential of Computer-Mediated Communication (CMC) to enable new forms of social interaction and foster democratisation of decision making has raised much interest but has bee...