References
Python documentation. https://docs.python.org/2/library/multiprocessing.html#multi-processing.Pipe. Accessed: 2019-07-16.
Martín Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, and Zhifeng Chen et al. TensorFlow: Large-scale machine learning on heterogeneous systems, 2015. Software available from http://tensorflow.org.
Greg Brockman, Vicki Cheung, Ludwig Pettersson, Jonas Schneider, John Schulman, Jie Tang, and Wojciech Zaremba. Openai gym, 2016.
Maxim Egorov. Multi-agent deep reinforcement learning. CS231n: Convolutional Neural Networks for Visual Recognition, 2016.
Carsten Hahn, Thomy Phan, Thomas Gabor, Lenz Belzner, and Claudia Linnhoff-Popien. Emergent escape-based flocking behavior using multi-agent reinforcement learning. In Conference on Artificial Life (ALIFE 2019), 2019.
Alexander Kuhnle, Michael Schaarschmidt, and Kai Fricke. Tensorforce: a tensorflow library for applied reinforcement learning. https://github.com/tensorforce/tensorforce, 2017. Accessed: 2019-07-16.
Eric Liang and Richard Liaw. Scaling multiagent reinforcement learning. https://bair.berkeley.edu/blog/2018/12/12/rllib/. Accessed: 2019-07-16.
Eric Liang, Richard Liaw, Philipp Moritz, Robert Nishihara, Roy Fox, Ken Goldberg, Joseph E. Gonzalez, Michael I. Jordan, and Ion Stoica. Rllib: Abstractions for distributed reinforcement learning, 2017.
Timothy P Lillicrap, Jonathan J Hunt, Alexander Pritzel, Nicolas Heess, Tom Erez, Yuval Tassa, David Silver, and Daan Wierstra. Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971, 2015.
Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A Rusu, Joel Veness, Marc G Bellemare, Alex Graves, Martin Riedmiller, Andreas K Fidjeland, Georg Ostrovski, et al. Human-level control through deep reinforcement learning. Nature, 518(7540):529, 2015.
Matthias Plappert. keras-rl. https://github.com/keras-rl/keras-rl, 2016. Accessed: 2019-07-16.
Theano Development Team. Theano: A Python framework for fast computation of mathematical expressions. arXiv e-prints, abs/1605.02688, May 2016.
Author information
Authors and Affiliations
Corresponding authors
Additional information
Carsten Hahn Carsten Hahn is a researcher at the LMU Munich. His research interests are artificial intelligence and autonomous systems.
Markus Friedrich Markus Friedrich is a researcher at the LMU Munich. His research focuses on 3D reconstruction based on point clouds/image series and machine learning.
Rights and permissions
About this article
Cite this article
Hahn, C., Friedrich, M. Using Existing Reinforcement Learning Libraries in Multi-Agent Scenarios. Digitale Welt 4, 62–66 (2020). https://doi.org/10.1007/s42354-019-0236-1
Published:
Issue Date:
DOI: https://doi.org/10.1007/s42354-019-0236-1