Enforcing Hard State-Dependent Action Bounds on Deep Reinforcement Learning Policies

Bram De Cooman, Johan A. K. Suykens, Andreas Ortseifen. Enforcing Hard State-Dependent Action Bounds on Deep Reinforcement Learning Policies. In Giuseppe Nicosia, Varun Ojha 0001, Emanuele La Malfa, Gabriele La Malfa, Panos M. Pardalos, Giuseppe Di Fatta, Giovanni Giuffrida, Renato Umeton, editors, Machine Learning, Optimization, and Data Science - 8th International Workshop, LOD 2022, Certosa di Pontignano, Italy, September 19-22, 2022, Revised Selected Papers, Part II. Volume 13811 of Lecture Notes in Computer Science, pages 193-218, Springer, 2022. [doi]

@inproceedings{CoomanSO22,
  title = {Enforcing Hard State-Dependent Action Bounds on Deep Reinforcement Learning Policies},
  author = {Bram De Cooman and Johan A. K. Suykens and Andreas Ortseifen},
  year = {2022},
  doi = {10.1007/978-3-031-25891-6_16},
  url = {https://doi.org/10.1007/978-3-031-25891-6_16},
  researchr = {https://researchr.org/publication/CoomanSO22},
  cites = {0},
  citedby = {0},
  pages = {193-218},
  booktitle = {Machine Learning, Optimization, and Data Science - 8th International Workshop, LOD 2022, Certosa di Pontignano, Italy, September 19-22, 2022, Revised Selected Papers, Part II},
  editor = {Giuseppe Nicosia and Varun Ojha 0001 and Emanuele La Malfa and Gabriele La Malfa and Panos M. Pardalos and Giuseppe Di Fatta and Giovanni Giuffrida and Renato Umeton},
  volume = {13811},
  series = {Lecture Notes in Computer Science},
  publisher = {Springer},
  isbn = {978-3-031-25891-6},
}