Abstract. Dyna is a single-agent architectural framework that integrates learning, planning, and reacting. Well known instantiations of Dyna are Dyna-AC and Dyna-Q. Here a multiage...
In this paper, a three-component architecture of a learning environment for Go is sketched, which can be applied to any two-player, deterministic, full information, partizan, comb...
Time varying environments or model selection problems lead to crucial dilemmas in identification and control science. In this paper, we propose a modular prediction scheme consisti...
We consider the problem of dialogue adaptation in our Smart Personal Assistant (SPA), which uses a plan-based dialogue model. We present a novel way of integrating learning into a...
The importance of aviation security has increased dramatically in recent years. Frequently changing regulations and the need to adapt quickly to new and emerging threats are chall...