Using Reward Machines for High-Level Task Specification and Decomposition in Reinforcement Learning

Using Reward Machines for High-Level Task Specification and Decomposition in Reinforcement Learning. Toro Icarte, R., Klassen, T. Q., Valenzano, R., & McIlraith, S. A. In Proceedings of the 35th International Conference on Machine Learning (ICML), pages 2112-2121, 2018.

Paper

Code bibtex 41 downloads

@inproceedings{tor-etal-icml18,
  author = {Rodrigo {Toro Icarte} and
            Toryn Q. Klassen and
            Richard Valenzano and
            Sheila A. McIlraith},
  title     = {Using Reward Machines for High-Level Task Specification and Decomposition in Reinforcement Learning},
  booktitle = {Proceedings of the 35th International Conference on Machine Learning (ICML)},
  year      = {2018},
  url = {http://proceedings.mlr.press/v80/icarte18a.html},
  url_code = {https://bitbucket.org/RToroIcarte/qrm},
  pages     = {2112-2121},
  keywords = {reward machines, reinforcement learning}
}

Downloads: 41