Supplementary Material for "The Effects on Adaptive Behaviour of Negatively Valenced Signals in Reinforcement Learning"

Nicolás Navarro-Guerrero, Robert Lowe, Stefan WermterFigshare 2017 · DOI · OpenAlex

Abstract

zip files with raw data from the 10 random initializations of the 4 best hyperparameter sets per condition and per activation function. Organized by function and per condition.<br><br>pdf file containing the pair-wise comparison of the three tested conditions against the baseline.<br><br>Link to the supplementary material of the original paper, includes matlab command and data set for learning:<br>https://figshare.com/s/becd4366e4ed38731353<br><b>References:<br></b>Navarro-Guerrero, N., Lowe, R., &amp; Wermter, S. (2017). The Effects on Adaptive Behaviour of Negatively Valenced Signals in Reinforcement Learning. In Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EPIROB) (pp. 148–155). Lisbon, Portugal: IEEE. https://doi.org/10.1109/DEVLRN.2017.8329800<br><br>Navarro-Guerrero, N., Lowe, R., &amp; Wermter, S. (2017). Improving Robot Motor Learning with Negatively Valenced Reinforcement Signals. Frontiers in Neurorobotics, 11(10). https://doi.org/10.3389/fnbot.2017.00010<br><b>Contact:</b>For information please see the paper. For specific questions regarding the paper please contact Nicolás Navarro-Guerrero.
BibTeX
@inproceedings{navarroguerrero2017supplementary,
  author = {Nicolás Navarro-Guerrero and Robert Lowe and Stefan Wermter},
  title = {{Supplementary Material for "The Effects on Adaptive Behaviour of Negatively Valenced Signals in Reinforcement Learning"}},
  booktitle = {Figshare},
  year = {2017},
  doi = {10.6084/m9.figshare.4585030},
}

Loading related content...

Figure