Poisoning finite-horizon Markov decision processes at design time
Year of publication: |
2021
|
---|---|
Authors: | Caballero, William N. ; Jenkins, Phillip R. ; Keith, Andrew J. |
Published in: |
Computers & operations research : and their applications to problems of world concern ; an international journal. - Oxford [u.a.] : Elsevier, ISSN 0305-0548, ZDB-ID 194012-0. - Vol. 129.2021, p. 1-17
|
Subject: | Adversarial learning | Data poisoning | Machine learning | Markov decision process | Reinforcement learning | Markov-Kette | Markov chain | Entscheidung | Decision | Künstliche Intelligenz | Artificial intelligence | Lernprozess | Learning process | Theorie | Theory | Lernen | Learning |
-
Reinforcement learning in economics and finance
Charpentier, Arthur, (2023)
-
Optimising darts strategy using Markov decision processes and reinforcement learning
Baird, Graham, (2020)
-
Kallus, Nathan, (2022)
- More ...
-
Predicting success in United States Air Force pilot training using machine learning techniques
Jenkins, Phillip R., (2022)
-
Robbins, Matthew J., (2020)
-
Jenkins, Phillip R., (2021)
- More ...