On discovery and learning of models with predictive representations of state for agents with continuous actions and observations

@inproceedings{Wingate2007OnDA,
  title={On discovery and learning of models with predictive representations of state for agents with continuous actions and observations},
  author={David Wingate and Satinder P. Singh},
  booktitle={AAMAS},
  year={2007}
}
Models of agent-environment interaction that use predictive state representations (PSRs) have mainly focused on the case of discrete observations and actions. The theory of discrete PSRs uses an elegant construct called the system dynamics matrix and derives the notion of predictive state as a sufficient statistic via the rank of the matrix. With continuous… CONTINUE READING