[Zurück]


Beiträge in Tagungsbänden:

D. Bechtold, A. Wendt, A. Jantsch:
"Evaluation of Reinforcement Learning Methods for a Self-learning System";
in: "Proceedings of the 12th International Conference on Agents and Artificial Intelligence (ICAART 2020)", Volume 2; herausgegeben von: SCITEPRESS - Science and Technology Publications, Lda.; SCITEPRESS - Science and Technology Publications, Lda., Portugal, 2020, ISBN: 978-989-758-395-7, S. 36 - 47.



Kurzfassung englisch:
In recent years, interest in self-learning methods has increased significantly. A challenge is to learn to survive
in a real or simulated world by solving tasks with as little prior knowledge about itself, the task, and the
environment. In this paper, the state of the art methods of reinforcement learning, in particular, Q-learning,
are analyzed regarding applicability to such a problem. The Q-learning algorithm is completed with replay
memories and exploration functions. Several small improvements are proposed. The methods are then
evaluated in two simulated environments: a discrete bit-flip and a continuous pendulum environment. The
result is a lookup table of the best suitable algorithms for each type of problem.

Schlagworte:
Reinforcement Learning, Machine Learning, Self-learning, Neural Networks, Q-learning, Deep Q-learning, Replay Memory, Artificial Intelligence, Rewards, Algorithms


Elektronische Version der Publikation:
https://publik.tuwien.ac.at/files/publik_288119.pdf


Erstellt aus der Publikationsdatenbank der Technischen Universität Wien.