Future agent applications will increasingly represent human users autonomously or semi-autonomously in strategic interactions with similar entities. Hence, there is a growing need...
Predictive State Representations (PSRs) have shown a great deal of promise as an alternative to Markov models. However, learning a PSR from a single stream of data generated from ...
We present the first temporal-difference learning algorithm for off-policy control with unrestricted linear function approximation whose per-time-step complexity is linear in the ...
We focus on the problem of efficient learning of dependency trees. Once grown, they can be used as a special case of a Bayesian network, for PDF approximation, and for many other u...
This paper presents a generative system for the automatic creation of video game levels. Our approach is novel in that it allows high-level design goals to be expressed in a top-do...