Decision-Making with Non-Markovian Rewards: Guiding search via automata-based reward shaping. Camacho, A., Chen, O., Sanner, S., & McIlraith, S. A. Technical Report CSRG-632, Department of Computer Science, University of Toronto, June, 2017.
Decision-Making with Non-Markovian Rewards: Guiding search via automata-based reward shaping [pdf]Paper  bibtex   14 downloads  

Downloads: 14