This paper examines the notion of symmetry in Markov decision processes (MDPs). We define symmetry for an MDP and show how it can be exploited for more effective learning in singl...
Abstract: This paper presents a multiagent architecture and algorithms for collaborative, self-organizing learning in distributed, heterogeneous and dynamic business systems, where...
contexts such as construction of abstractions, speed may be favored over completeness, so that undecidable theories (e.g., nonlinear integer arithmetic) and those whose decision pr...
Solving complex global problems such as illegal immigration, border control, and terrorism requires government organizations at all levels to share not only data but, more importa...
Seema Degwekar, Jeff DePree, Howard W. Beck, Carla...