Federico Espositi, Andrea Bonarini. Policy Feedback in Deep Reinforcement Learning to Exploit Expert Knowledge. In Giuseppe Nicosia, Varun Kumar Ojha, Emanuele La Malfa, Giorgio Jansen, Vincenzo Sciacca, Panos M. Pardalos, Giovanni Giuffrida, Renato Umeton, editors, Machine Learning, Optimization, and Data Science - 6th International Conference, LOD 2020, Siena, Italy, July 19-23, 2020, Revised Selected Papers, Part I. Volume 12565 of Lecture Notes in Computer Science, pages 269-272, Springer, 2020. [doi]
@inproceedings{EspositiB20,
title = {Policy Feedback in Deep Reinforcement Learning to Exploit Expert Knowledge},
author = {Federico Espositi and Andrea Bonarini},
year = {2020},
doi = {10.1007/978-3-030-64583-0_25},
url = {https://doi.org/10.1007/978-3-030-64583-0_25},
researchr = {https://researchr.org/publication/EspositiB20},
cites = {0},
citedby = {0},
pages = {269-272},
booktitle = {Machine Learning, Optimization, and Data Science - 6th International Conference, LOD 2020, Siena, Italy, July 19-23, 2020, Revised Selected Papers, Part I},
editor = {Giuseppe Nicosia and Varun Kumar Ojha and Emanuele La Malfa and Giorgio Jansen and Vincenzo Sciacca and Panos M. Pardalos and Giovanni Giuffrida and Renato Umeton},
volume = {12565},
series = {Lecture Notes in Computer Science},
publisher = {Springer},
isbn = {978-3-030-64583-0},
}