Folgen
Michel Tokic
Michel Tokic
Siemens AG, Munich
Bestätigte E-Mail-Adresse bei tokic.com - Startseite
Titel
Zitiert von
Zitiert von
Jahr
Adaptive ε-Greedy Exploration in Reinforcement Learning Based on Value Differences
M Tokic
Annual conference on artificial intelligence, 203-210, 2010
4922010
Value-difference based exploration: adaptive control between epsilon-greedy and softmax
M Tokic, G Palm
KI 2011: Advances in Artificial Intelligence, 335-346, 2011
3302011
Modeling system dynamics with physics-informed neural networks based on Lagrangian mechanics
MA Roehrl, TA Runkler, V Brandtstetter, M Tokic, S Obermayer
IFAC-PapersOnLine 53 (2), 9195-9200, 2020
982020
A benchmark environment motivated by industrial control problems
D Hein, S Depeweg, M Tokic, S Udluft, A Hentschel, TA Runkler, ...
2017 IEEE Symposium Series on Computational Intelligence (SSCI), 1-8, 2017
692017
The crawler, a class room demonstrator for reinforcement learning
M Tokic, W Ertel, J Fessler
Twenty-Second International FLAIRS Conference, 2009
352009
The teaching-box: A universal robot learning framework
W Ertel, M Schneider, R Cubek, M Tokicy
Advanced Robotics, 2009. ICAR 2009. International Conference on, 1-6, 2009
302009
Batch reinforcement learning on the industrial benchmark: First experiences
D Hein, S Udluft, M Tokic, A Hentschel, TA Runkler, V Sterzing
2017 International Joint Conference on Neural Networks (IJCNN), 4214-4221, 2017
182017
Teaching Reinforcement Learning Using a Physical Robot
M Tokic, H Bou Ammar
Proceedings of the Workshop on Teaching Machine Learning at the 29th …, 2012
132012
Gradient algorithms for exploration/exploitation trade-offs: Global and local variants
M Tokic, G Palm
Artificial Neural Networks in Pattern Recognition: 5th INNS IAPR TC 3 GIRPR …, 2012
92012
Meta-learning of exploration and exploitation parameters with replacing eligibility traces
M Tokic, F Schwenker, G Palm
IAPR International Workshop on Partially Supervised Learning, 68-79, 2013
82013
Entwicklung eines lernenden laufroboters
M Tokic
Diplomarbeit, Hochschule Ravensburg-Weingarten, Doggenriedstrasse, 88250 …, 2006
82006
Towards Learning of Safety Knowledge from Human Demonstrations
P Ertle, M Tokic, R Cubek, H Voos, D Söffker
International Conference on Intelligent Robots and Systems (IROS), 1-6, 2012
72012
Adaptive exploration using stochastic neurons
M Tokic, G Palm
Artificial Neural Networks and Machine Learning–ICANN 2012: 22nd …, 2012
72012
Introduction to the" Industrial Benchmark"
D Hein, A Hentschel, V Sterzing, M Tokic, S Udluft
arXiv preprint arXiv:1610.03793, 2016
62016
Robust Exploration/Exploitation trade-offs in safety-critical applications
M Tokic, P Ertle, G Palm, D Söffker, H Voos
IFAC Proceedings Volumes 45 (20), 660-665, 2012
62012
Reinforcement Learning mit adaptiver Steuerung von Exploration und Exploitation
M Tokic
Universität Ulm, 2016
52016
Reinforcement Learning: Psychologische und neurobiologische Aspekte
M Tokic
Künstliche Intelligenz 27 (3), 213-219, 2013
52013
Entwicklung eines lernfähigen Laufroboters
M Tokic
Diplomarbeit Hochschule Ravensburg-Weingarten, 2006. Inklusive …, 2006
52006
Reinforcement learning on a simple real walking robot
M Tokic, W Ertel, HP Radtke, J Akmal, W Krökel
Proceedings of the 29th Annual German Conference on Artificial Intelligence …, 2006
32006
Management of processes with temporal development into the past, in particular of processes taking place at the same time in industrial installations, with the aid of neural …
M Tokic, A Von Beuningen, N Körwer, M Bischoff, D Grossenbacher, ...
US Patent App. 18/214,121, 2024
22024
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–20