Stefan Elfwing, Ben Seymour. Parallel reward and punishment control in humans and robots: Safe reinforcement learning using the MaxPain algorithm. In 2017 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics, ICDL-EpiRob 2017, Lisbon, Portugal, September 18-21, 2017. pages 140-147, IEEE, 2017. [doi]
@inproceedings{ElfwingS17,
title = {Parallel reward and punishment control in humans and robots: Safe reinforcement learning using the MaxPain algorithm},
author = {Stefan Elfwing and Ben Seymour},
year = {2017},
doi = {10.1109/DEVLRN.2017.8329799},
url = {https://doi.org/10.1109/DEVLRN.2017.8329799},
researchr = {https://researchr.org/publication/ElfwingS17},
cites = {0},
citedby = {0},
pages = {140-147},
booktitle = {2017 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics, ICDL-EpiRob 2017, Lisbon, Portugal, September 18-21, 2017},
publisher = {IEEE},
isbn = {978-1-5386-3715-9},
}