This paper addresses the need for formal specification and runtime verification of system-level requirements of distributed reactive systems. It describes a formalism for specifyi...
Simulated evolution by the use of Genetic Algorithms (GA) is presented as the solution to a twofaceted problem: the challenge for an autonomous agent to learn the reactive componen...
In this paper we describe Lokutor, a virtual human. Lokutor is a partially autonomous agent, inhabiting a 3D virtual environment. The agent can be controlled via natural language ...
PROPAGATOR is a family of patterns for consistently updating objects in a dependency network. The propagator patterns are found in such diverse applications as MAKE, WWW, spreadsh...
Policy gradient methods for reinforcement learning avoid some of the undesirable properties of the value function approaches, such as policy degradation (Baxter and Bartlett, 2001...
Evan Greensmith, Peter L. Bartlett, Jonathan Baxte...