Abstract
Multi Agent Reinforcement Learning (MARL) is an emerging field in machine learning where multiple agents learn, simultaneously and in a shared environment, how to optimise a global or local reward signal. MARL has gained significant interest in recent years due to its successful applications in various domains, such as robotics, IoT, and traffic control. Cooperative Many Agent Reinforcement Learning (CMARL) is a relevant subclass of MARL, where thousands of agents work together to achieve a common coordination goal.
In this paper, we introduce ScaRLib, a Scala framework relying on state-of-the-art deep learning libraries to support the development of CMARL systems. The framework supports the specification of centralised training and decentralised execution, and it is designed to be easily extensible, allowing to add new algorithms, new types of environments, and new coordination toolchains.
This paper describes the main structure and features of ScaRLib and includes basic demonstrations that showcase binding with one such toolchain: ScaFi programming framework and Alchemist simulator can be exploited to enable learning of field-based coordination policies for large-scale systems.
Supported by Department of Computer Science and Engineering @ Alma Mater Studiorum - University of Bologna.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
- 3.
Tool available on GitHub at https://github.com/ScaRLib-group/ScaRLib.
- 4.
Demo video at: https://github.com/ScaRLib-group/ScaRLib-demo-video.
- 5.
- 6.
- 7.
- 8.
Repository available at https://github.com/ScaRLib-group/ScaRLib-flock-demo.
- 9.
References
Aguzzi, G.: Research directions for aggregate computing with machine learning. In: 2021 IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C). IEEE (2021). https://doi.org/10.1109/acsos-c52956.2021.00078
Aguzzi, G., Casadei, R., Pianini, D., Viroli, M.: Dynamic decentralization domains for the internet of things. IEEE Internet Comput. 26(6), 16–23 (2022). https://doi.org/10.1109/mic.2022.3216753
Aguzzi, G., Casadei, R., Viroli, M.: Addressing collective computations efficiency: Towards a platform-level reinforcement learning approach. In: Casadei, R., et al. (eds.) IEEE International Conference on Autonomic Computing and Self-Organizing Systems, ACSOS 2022, Virtual, CA, USA, 19–23 September 2022, pp. 11–20. IEEE (2022). https://doi.org/10.1109/ACSOS55765.2022.00019
Aguzzi, G., Casadei, R., Viroli, M.: Machine learning for aggregate computing: a research roadmap. In: 2022 IEEE 42nd International Conference on Distributed Computing Systems Workshops (ICDCSW). IEEE (2022). https://doi.org/10.1109/icdcsw56584.2022.00032
Aguzzi, G., Casadei, R., Viroli, M.: Towards reinforcement learning-based aggregate computing. In: ter Beek, M.H., Sirjani, M. (eds) Coordination Models and Languages. COORDINATION 2022. IFIP Advances in Information and Communication Technology, vol. 13271, pp. 72–91. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-08143-9_5
Baker, B., et al.: Emergent tool use from multi-agent autocurricula (2019). https://doi.org/10.48550/ARXIV.1909.07528. https://arxiv.org/abs/1909.07528
Beal, J., Pianini, D., Viroli, M.: Aggregate programming for the internet of things. Computer 48(9), 22–30 (2015). https://doi.org/10.1109/mc.2015.261
Bettini, M., Kortvelesy, R., Blumenkamp, J., Prorok, A.: VMAS: a vectorized multi-agent simulator for collective robot learning. The 16th International Symposium on Distributed Autonomous Robotic Systems (2022)
Busoniu, L., Babuska, R., Schutter, B.D.: A comprehensive survey of multiagent reinforcement learning. IEEE Trans. Syst. Man Cybern. Part C (Appl. Rev.) 38(2), 156–172 (2008). https://doi.org/10.1109/tsmcc.2007.913919
Casadei, R.: Macroprogramming: Concepts, state of the art, and opportunities of macroscopic behaviour modelling. ACM Computing Surveys (2023). https://doi.org/10.1145/3579353
Casadei, R., Viroli, M., Aguzzi, G., Pianini, D.: ScaFi: a scala DSL and toolkit for aggregate programming. SoftwareX 20, 101248 (2022). https://doi.org/10.1016/j.softx.2022.101248
Casadei, R., Viroli, M., Audrito, G., Pianini, D., Damiani, F.: Engineering collective intelligence at the edge with aggregate processes. Eng. Appl. Artif. Intell. 97, 104081 (2021). https://doi.org/10.1016/j.engappai.2020.104081
Chu, T., Wang, J., Codecà, L., Li, Z.: Multi-agent deep reinforcement learning for large-scale traffic signal control (2019). https://doi.org/10.48550/ARXIV.1903.04527. https://arxiv.org/abs/1903.04527
Du, W., Ding, S.: A survey on multi-agent deep reinforcement learning: from the perspective of challenges and applications. Artif. Intell. Rev. 54(5), 3215–3238 (2020). https://doi.org/10.1007/s10462-020-09938-y
Fey, M., Lenssen, J.E.: Fast graph representation learning with pyTorch geometric (2019)
He, K., Doshi, P., Banerjee, B.: Many agent reinforcement learning under partial observability (2021). https://doi.org/10.48550/ARXIV.2106.09825. https://arxiv.org/abs/2106.09825
Hüttenrauch, M., Adrian, S., Neumann, G., et al.: Deep reinforcement learning for swarm systems. J. Mach. Learn. Res. 20(54), 1–31 (2019)
Laddad, S., Sen, K.: ScalaPy: seamless python interoperability for cross-platform scala programs. In: Proceedings of the 11th ACM SIGPLAN International Symposium on Scala. ACM (2020). https://doi.org/10.1145/3426426.3428485
Lei, L., Tan, Y., Zheng, K., Liu, S., Zhang, K., Shen, X.: Deep reinforcement learning for autonomous internet of things: Model, applications and challenges. IEEE Commun. Surv. Tutorials 22(3), 1722–1760 (2020). https://doi.org/10.1109/comst.2020.2988367
Littman, M.L.: Markov games as a framework for multi-agent reinforcement learning. In: Cohen, W.W., Hirsh, H. (eds.) Machine Learning Proceedings 1994, pp. 157–163. Morgan Kaufmann, San Francisco (CA) (1994). https://doi.org/10.1016/B978-1-55860-335-6.50027-1. https://www.sciencedirect.com/science/article/pii/B9781558603356500271
Long, P., Fanl, T., Liao, X., Liu, W., Zhang, H., Pan, J.: Towards optimally decentralized multi-robot collision avoidance via deep reinforcement learning. In: 2018 IEEE International Conference on Robotics and Automation (ICRA). IEEE (2018). https://doi.org/10.1109/icra.2018.8461113
Mnih, V., et al.: Playing Atari with deep reinforcement learning (2013). https://doi.org/10.48550/ARXIV.1312.5602. https://arxiv.org/abs/1312.5602
Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529–533 (2015). https://doi.org/10.1038/nature14236
Moritz, P., et al.: Ray: a distributed framework for emerging AI applications (2017). https://doi.org/10.48550/ARXIV.1712.05889. https://arxiv.org/abs/1712.05889
Pianini, D., Montagna, S., Viroli, M.: Chemical-oriented simulation of computational systems with ALCHEMIST. J. Simulation 7(3), 202–215 (2013). https://doi.org/10.1057/jos.2012.27
Reynolds, C.W.: Flocks, herds and schools: a distributed behavioral model. In: Stone, M.C. (ed.) Proceedings of the 14th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1987, Anaheim, California, USA, 27–31 July 1987, pp. 25–34. ACM (1987). https://doi.org/10.1145/37401.37406
Richmond, P., Coakley, S., Romano, D.M.: A high performance agent based modelling framework on graphics card hardware with Cuda. In: Proceedings of The 8th International Conference on Autonomous Agents and Multiagent Systems - Volume 2, pp. 1125–1126. AAMAS 2009, International Foundation for Autonomous Agents and Multiagent Systems, Richland, SC (2009)
Samvelyan, M., et al.: The starcraft multi-agent challenge (2019). https://doi.org/10.48550/ARXIV.1902.04043. https://arxiv.org/abs/1902.04043
Samvelyan, M., et al.: The StarCraft Multi-Agent Challenge. CoRR abs/1902.04043 (2019)
Suarez, J., Du, Y., Isola, P., Mordatch, I.: Neural MMO: a massively multiagent game environment for training and evaluating intelligent agents (2019). https://doi.org/10.48550/ARXIV.1903.00784. https://arxiv.org/abs/1903.00784
Terry, J., et al.: PettingZoo: Gym for multi-agent reinforcement learning. In: Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems. vol. 34, pp. 15032–15043. Curran Associates, Inc. (2021). https://proceedings.neurips.cc/paper/2021/file/7ed2d3454c5eea71148b11d0c25104ff-Paper.pdf
Watkins, C.J.C.H., Dayan, P.: Q-learning. Mach. Learn. 8(3-4), 279–292 (1992). https://doi.org/10.1007/bf00992698
Yang, Y.: Many-agent reinforcement learning, Ph. D. thesis, UCL (University College London) (2021)
Yang, Y., Luo, R., Li, M., Zhou, M., Zhang, W., Wang, J.: Mean field multi-agent reinforcement learning (2018). https://doi.org/10.48550/ARXIV.1802.05438. https://arxiv.org/abs/1802.05438
Yu, C., et al.: The surprising effectiveness of PPO in cooperative, multi-agent games (2021). https://doi.org/10.48550/ARXIV.2103.01955. https://arxiv.org/abs/2103.01955
Šošić, A., KhudaBukhsh, W.R., Zoubir, A.M., Koeppl, H.: Inverse reinforcement learning in swarm systems (2016). https://doi.org/10.48550/ARXIV.1602.05450. https://arxiv.org/abs/1602.05450
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 IFIP International Federation for Information Processing
About this paper
Cite this paper
Domini, D., Cavallari, F., Aguzzi, G., Viroli, M. (2023). ScaRLib: A Framework for Cooperative Many Agent Deep Reinforcement Learning in Scala. In: Jongmans, SS., Lopes, A. (eds) Coordination Models and Languages. COORDINATION 2023. Lecture Notes in Computer Science, vol 13908. Springer, Cham. https://doi.org/10.1007/978-3-031-35361-1_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-35361-1_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-35360-4
Online ISBN: 978-3-031-35361-1
eBook Packages: Computer ScienceComputer Science (R0)