In this paper, we show how the dynamics of Q-learning can be visualized and analyzed from a perspective of Evolutionary Dynamics (ED). More specifically, we show how ED can be use...
Decentralized Markov decision processes are frequently used to model cooperative multi-agent systems. In this paper, we identify a subclass of general DEC-MDPs that features regul...
Most current theories about collective cognitive activities in limited groups apply to structurally closed co-operative situations Here we propose to work in the framework of inte...
Thecurrent frameworkfor constructing intelligent tutoring systems(ITS) is to use psychological/pedagogical theories of learning, and encode this knowledgeinto the tutor. However,t...
Imitation is actively being studied as an effective means of learning in multi-agent environments. It allows an agent to learn how to act well (perhaps optimally) by passively obs...