Abstract
Cooperative-competitive social group dynamics may be modelled with multi-agent environments with a large number of agents from a few distinct agent-types. Even the simplest games modelling social interactions are suitable to analyze emerging group dynamics. In many cases, the underlying computational problem is NP-complex, thus various machine learning techniques are implemented to accelerate the optimization process. Multi-agent reinforcement learning provides an effective framework to train autonomous agents with an adaptive nature. We analyze the performance of centralized and decentralized training featuring Deep Q-Networks on cooperative-competitive environments introduced in the MAgent library. Our experiments demonstrate that sensible policies may be constructed utilizing centralized and decentralized reinforcement learning methods by observing the mean rewards accumulated during training episodes.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Aymanns, C., Foerster, J., Georg, C.-P.: Fake news in social networks. SSRN Electr. J. Paper No. 2018/4 (2017)
Bloembergen, D., Tuyls, K., Hennes, D., Kaisers, M.: Evolutionary dynamics of multi-agent learning: a survey. J. Artif. Intell. Res. 53, 659–697 (2015)
Brooks, R.A.: Intelligence without representation. Artif. Intell. 47(1), 139–159 (1991)
Cai, C., Yang, C., Zhu, Q., Liang, Y.: Collision avoidance in multi-robot systems. In: 2007 International Conference on Mechatronics and Automation, pp. 2795–2800 (2007)
Cai, P., Lee, Y., Luo, Y., Hsu, D.: Summit: A simulator for urban driving in massive mixed traffic. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 4023–4029. IEEE (2020)
Carley, K., Martin, M., Hirshman, B.: The etiology of social change. Top. Cogn. Sci. 1, 621–650 (2009)
Dechter, R., Meiri, I., Pearl, J.: Temporal constraint networks. Artif. Intell. 49(1), 61–95 (1991)
dos Santos, D.S., Bazzan, A.L.: Distributed clustering for group formation and task allocation in multiagent systems: a swarm intelligence approach. Appl. Soft Comput. 12(8), 2123–2131 (2012)
Gupta, J.K., Egorov, M., Kochenderfer, M.: Cooperative multi-agent control using deep reinforcement learning. In: Sukthankar, G., Rodriguez-Aguilar, J.A. (eds.) AAMAS 2017. LNCS (LNAI), vol. 10642, pp. 66–83. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-71682-4_5
Herrera, M., Pérez-Hernández, M., Kumar Parlikad, A., Izquierdo, J.: Multi-agent systems and complex networks: review and applications in systems engineering. Processes 8(3), 312 (2020)
Kossinets, G., Watts, D.J.: Empirical analysis of an evolving social network. Science 311, 88–90 (2006)
Leibo, J. Z., et al.: Scalable evaluation of multi-agent reinforcement learning with melting pot. In: International Conference on Machine Learning, pp. 6187–6199. PMLR (2021)
Leibo, J.Z., Zambaldi, V., Lanctot, M., Marecki, J., Graepel, T.: Multi-agent reinforcement learning in sequential social dilemmas. In: Proceedings of the 16th Conference on Autonomous Agents and MultiAgent Systems, AAMAS ’17, pp. 464–473 (2017)
Li, J.-Q., Mirchandani, P.B., Borenstein, D.: The vehicle rescheduling problem: model and algorithms. Networks 50(3), 211–229 (2007)
Liang, E., et al.: Ray RLlib: A composable and scalable reinforcement learning library. arXiv preprint arXiv:abs/1712.09381 (2017)
Liu, S., Lever, G., Merel, J., Tunyasuvunakool, S., Heess, N., Graepel, T.: Emergent coordination through competition. arXiv preprint arXiv:abs/1902.07151 (2019)
Mnih, V., et al.: Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)
Mordatch, I., Abbeel, P.: Emergence of grounded compositional language in multi-agent populations. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)
Nicosia, V., Tang, J., Musolesi, M., Russo, G., Mascolo, C., Latora, V.: Components in time-varying graphs. Chaos: Interdisc. J. Nonlinear. Sci. 22(2), 023101 (2012)
Nowé, A., Vrancx, P., Hauwere, Y.-M.D.: Game theory and multi-agent reinforcement learning. In: Wiering, M., van Otterlo, M. (eds) Reinforcement Learning. Adaptation, Learning, and Optimization, pp. 441–470. Springer, Berlin, Heidelberg (2012). https://doi.org/10.1007/978-3-642-27645-3_14
Papoudakis, G., Christianos, F., Schäfer, L., Albrecht, S.V.: Benchmarking multi-agent deep reinforcement learning algorithms in cooperative tasks. In: Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks (NeurIPS) (2021)
Rashid, T., Samvelyan, M., Witt, C.S.D., Farquhar, G., Foerster, J.N., Whiteson, S.: Monotonic value function factorisation for deep multi-agent reinforcement learning. J. Mach. Learn. Res. 21, 178:1–178:51 (2020)
Stehlé, J.: Simulation of an SEIR infectious disease model on the dynamic contact network of conference attendees. BMC Med. 9(1), 1–15 (2011)
Sunehag, P., et al.: Value-decomposition networks for cooperative multi-agent learning based on team reward. In: Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems, AAMAS ’18, pp. 2085–2087 (2018)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, 2nd edn. The MIT Press (2018)
Tan, M.: Multi-agent reinforcement learning: Independent vs. cooperative agents. In: Proceedings of the Tenth International Conference on Machine Learning, pp. 330–337. Morgan Kaufmann (1993)
Terry, J.K., et al.: PettingZoo: Gym for multi-agent reinforcement learning. arXiv preprint arXiv:2009.14471 (2020)
Törnquist, J., Persson, J., et al.: Train traffic deviation handling using tabu search and simulated annealing. In: Proceedings of the 38th Hawaii International Conference on System Sciences, pp. 1–10 (2005)
Vinyals, O., et al.: Starcraft II: A new challenge for reinforcement learning. arXiv preprint arXiv:abs/1708.04782 (2017)
Vrancx, P., Verbeeck, K., Nowe, A.: Decentralized learning in Markov games. Part B, Cybern.: a publication of the IEEE Syst., Man, Cybern. Soc. 38, 976–981 (2008)
Wang, L., Wang, Z., Hu, S., Liu, L.: Ant colony optimization for task allocation in multi-agent systems. China Commun. 10(3), 125–132 (2013)
Yang, Y., Luo, R., Li, M., Zhou, M., Zhang, W., Wang, J.: Mean field multi-agent reinforcement learning. In: Dy, J., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning, vol. 80 of Proceedings of Machine Learning Research, pp. 5571–5580. PMLR (2018)
Zhang, T., Ye, Q., Bian, J., Xie, G., Liu, T.-Y.: MFVFD: a multi-agent Q-learning approach to cooperative and non-cooperative tasks. In: Zhou, Z.-H. (ed.) Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21, pp. 500–506 (2021)
Zheng, L., et al.: MAgent: A many-agent reinforcement learning platform for artificial collective intelligence. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Kopacz, A., Csató, L., Chira, C. (2023). Applying Deep Q-learning for Multi-agent Cooperative-Competitive Environments. In: García Bringas, P., et al. 17th International Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO 2022). SOCO 2022. Lecture Notes in Networks and Systems, vol 531. Springer, Cham. https://doi.org/10.1007/978-3-031-18050-7_61
Download citation
DOI: https://doi.org/10.1007/978-3-031-18050-7_61
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-18049-1
Online ISBN: 978-3-031-18050-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)