Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Marie Ossenkopf"'
Publikováno v:
Cybernetics and Systems. 50:672-692
Multi-agent systems need to communicate to coordinate a shared task. We show that a recurrent neural network (RNN) can learn a communication protocol for coordination, even if the actions t...
Publikováno v:
Procedia Manufacturing. 11:329-337
Reinforcement Learning algorithms have the downside of potentially dangerous exploration of unknown states, which makes them largely unsuitable for the use on serial manipulators in an industrial setting. In this paper, we make use of a policy search
Publikováno v:
ECMR
Exploring efficiently an unknown environment with several autonomous agents is a challenging task. In this work we propose an multi-agent Active SLAM method that is able to evaluate a long planning horizon of actions and perform exploration while mai
Publikováno v:
SAC
Multi-agent systems need to communicate to coordinate a shared task. We show that a recurrent neural network (RNN) can learn a communication protocol for coordination, even if the actions to coordinate lie outside of the communication range. We also
Publikováno v:
RoboCup 2019: Robot World Cup XXIII ISBN: 9783030356989
RoboCup
RoboCup
The RoboCup is an international competition in robot science. In the Middle Size League (MSL), which is one of the robotic soccer leagues, dribbling a ball is an essential capability. This task needs both hardware and software consideration. The posi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1ae6379fe29d143821b28299883c2673
https://doi.org/10.1007/978-3-030-35699-6_3
https://doi.org/10.1007/978-3-030-35699-6_3