This paper describes an online learning method of color transformation for interactive object recognition. In order to recognize objects under various lighting conditions, the sys...
Predictive state representations (PSRs) have recently been proposed as an alternative to partially observable Markov decision processes (POMDPs) for representing the state of a dy...
Matthew Rosencrantz, Geoffrey J. Gordon, Sebastian...
In this article, we present an idea for solving deterministic partially observable markov decision processes (POMDPs) based on a history space containing sequences of past observat...
If one has attributed certain initial beliefs to an agent, it is sometimes possible to reason about further beliefs the agent must hold by observing what conclusions one's ow...
We describe an effort to train a RoboCup soccer-playing agent playing in the Simulation League using casebased reasoning. The agent learns (builds a case base) by observing the be...