Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Gronauer, Sven"'
Reinforcement learning algorithms need exploration to learn. However, unsupervised exploration prevents the deployment of such algorithms on safety-critical tasks and limits real-world deployment. In this paper, we propose a new algorithm called Ense
Externí odkaz:
http://arxiv.org/abs/2402.04182
Publikováno v:
2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
In this work, we propose a data-driven approach to optimize the parameters of a simulation such that control policies can be directly transferred from simulation to a real-world quadrotor. Our neural network-based policies take only onboard sensor da
Externí odkaz:
http://arxiv.org/abs/2201.01369
Recent development of Deep Reinforcement Learning (DRL) has demonstrated superior performance of neural networks in solving challenging problems with large or even continuous state spaces. One specific approach is to deploy neural networks to approxi
Externí odkaz:
http://arxiv.org/abs/2106.08774
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Gronauer, Sven, Diepold, Klaus
Publikováno v:
Artificial Intelligence Review; Feb2022, Vol. 55 Issue 2, p895-943, 49p
