Abstract
Inspired by the centralised training with decentralised execution (CTDE) paradigm, the field of multi-agent reinforcement learning (MARL) has made significant progress in tackling cooperative problems with discrete action spaces. Nevertheless, many existing algorithms suffer from significant performance degradation when faced with large numbers of agents or more challenging tasks. Furthermore, some specific scenarios, such as cooperative environments with penalties, pose significant challenges to these algorithms , which often lack sufficient cooperative behavior to converge successfully. A new approach, called PRACM, based on the Actor-Critic framework is proposed in this study to address these issues. PRACM employs a monotonic mixing function to generate a global action value function, \(Q_{tot}\), which is used to compute the loss function for updating the critic network. To handle the discrete action space, PRACM uses Gumbel-Softmax. And to promote cooperation among agents and to adapt to cooperative environments with penalties, the predictive rewards is introduced. PRACM was evaluated against several baseline algorithms in “Cooperative Predator-Prey” and the challenging “SMAC” scenarios. The results of this study illustrate that PRACM scales well as the number of agents and task difficulty increase, and performs better in cooperative tasks with penalties, demonstrating its usefulness in promoting collaboration among agents.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Böhmer, W., Kurin, V., Whiteson, S.: Deep coordination graphs. In: International Conference on Machine Learning. pp. 980–991. PMLR (2020)
Haarnoja, T., et al.: Soft actor-critic algorithms and applications. arXiv preprint arXiv:1812.05905 (2018)
Hao, J., et al.: Exploration in deep reinforcement learning: from single-agent to multiagent domain. IEEE Trans. Neural Netw. Learn. Syst. (2023)
He, W., Chen, T.: Scalable online disease diagnosis via multi-model-fused actor-critic reinforcement learning. arXiv preprint arXiv:2206.03659 (2022)
Jang, E., Gu, S., Poole, B.: Categorical reparameterization with gumbel-softmax. arXiv preprint arXiv:1611.01144 (2016)
Kim, D., et al.: Learning to schedule communication in multi-agent reinforcement learning. arXiv preprint arXiv:1902.01554 (2019)
Kraemer, L., Banerjee, B.: Multi-agent reinforcement learning as a rehearsal for decentralized planning. Neurocomputing 190, 82–94 (2016)
Li, J., Wu, F., Shi, H., Hwang, K.S.: A collaboration of multi-agent model using an interactive interface. Inf. Sci. 611, 349–363 (2022)
Li, W., Liu, W., Shao, S., Huang, S., Song, A.: Attention-based intrinsic reward mixing network for credit assignment in multi-agent reinforcement learning. IEEE Trans. Games (2023)
Lowe, R., Wu, Y.I., Tamar, A., Harb, J., Pieter Abbeel, O., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. Adv. Inf. Process. Syst. 30 (2017)
Ma, Z., Wang, R., Li, F.F., Bernstein, M., Krishna, R.: Elign: Expectation alignment as a multi-agent intrinsic reward. Adv. Neural Inf. Process. Syst. 35, 8304–8317 (2022)
Ndousse, K.K., Eck, D., Levine, S., Jaques, N.: Emergent social learning via multi-agent reinforcement learning. In: International Conference on Machine Learning. pp. 7991–8004. PMLR (2021)
Omidshafiei, S., et al.: Learning to teach in cooperative multiagent reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 33, pp. 6128–6136 (2019)
Peng, B., et al.: Facmac: Factored multi-agent centralised policy gradients. Adv. Neural Inf. Process. Syst. 34, 12208–12221 (2021)
Pina, R., De Silva, V., Hook, J., Kondoz, A.: Residual q-networks for value function factorizing in multiagent reinforcement learning. IEEE Trans. Neural Netw. Learn. Syst. (2022)
Prajapat, M., Turchetta, M., Zeilinger, M., Krause, A.: Near-optimal multi-agent learning for safe coverage control. Adv. Neural Inf. Process. Syst. 35, 14998–15012 (2022)
Puente-Castro, A., Rivero, D., Pazos, A., Fernandez-Blanco, E.: A review of artificial intelligence applied to path planning in UAV swarms. Neural Comput. Appl. 34(1), 153–170 (2021). https://doi.org/10.1007/s00521-021-06569-4
Rashid, T., Samvelyan, M., De Witt, C.S., Farquhar, G., Foerster, J., Whiteson, S.: Monotonic value function factorisation for deep multi-agent reinforcement learning. J. Mach. Learn. Res. 21(1), 7234–7284 (2020)
Ryu, H., Shin, H., Park, J.: Multi-agent actor-critic with hierarchical graph attention network. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 34, pp. 7236–7243 (2020)
Sahoo, S., Lo, C.Y.: Smart manufacturing powered by recent technological advancements: a review. J. Manuf. Syst. 64, 236–250 (2022)
Samvelyan, M., et al.: The starcraft multi-agent challenge. arXiv preprint arXiv:1902.04043 (2019)
Sharma, R., Shishodia, A., Gunasekaran, A., Min, H., Munim, Z.H.: The role of artificial intelligence in supply chain management: mapping the territory. Int. J. Prod. Res. 60(24), 7527–7550 (2022)
Son, K., Kim, D., Kang, W.J., Hostallero, D.E., Yi, Y.: Qtran: Learning to factorize with transformation for cooperative multi-agent reinforcement learning. In: International conference on machine learning. pp. 5887–5896. PMLR (2019)
Wang, J., Ren, Z., Liu, T., Yu, Y., Zhang, C.: QPLEX: Duplex dueling multi-agent q-learning. arXiv preprint arXiv:2008.01062 (2020)
Wang, J., Li, Y., Gao, R.X., Zhang, F.: Hybrid physics-based and data-driven models for smart manufacturing: Modelling, simulation, and explainability. J. Manuf. Syst. 63, 381–391 (2022)
Wang, Y., Han, B., Wang, T., Dong, H., Zhang, C.: Off-policy multi-agent decomposed policy gradients. arXiv preprint arXiv:2007.12322 (2020)
Wang, Z., Li, M., Lu, J., Cheng, X.: Business innovation based on artificial intelligence and blockchain technology. Inf. Process. Manag. 59(1), 102759 (2022)
Wang, Z., Schaul, T., Hessel, M., Hasselt, H., Lanctot, M., Freitas, N.: Dueling network architectures for deep reinforcement learning. In: International conference on machine learning. pp. 1995–2003. PMLR (2016)
Wen, M., et al.: Multi-agent reinforcement learning is a sequence modeling problem. Adv. Neural Inf. Process. Syst. 35, 16509–16521 (2022)
Yang, J., Ni, J., Li, Y., Wen, J., Chen, D.: The intelligent path planning system of agricultural robot via reinforcement learning. Sensors 22(12), 4316 (2022)
Yang, T., et al.: Exploration in deep reinforcement learning: a comprehensive survey. arXiv preprint arXiv:2109.06668 (2021)
Ye, Z., Chen, Y., Jiang, X., Song, G., Yang, B., Fan, S.: Improving sample efficiency in Multi-Agent Actor-Critic methods. Appl. Intell. 1–14 (2021). https://doi.org/10.1007/s10489-021-02554-5
Zhang, T., Li, Y., Wang, C., Xie, G., Lu, Z.: Fop: Factorizing optimal joint policy of maximum-entropy multi-agent reinforcement learning. In: International Conference on Machine Learning. pp. 12491–12500. PMLR (2021)
Zhang, T., Liu, Z., Wu, S., Pu, Z., Yi, J.: Intrinsic reward with peer incentives for cooperative multi-agent reinforcement learning. In: 2022 International Joint Conference on Neural Networks (IJCNN). pp. 1–7. IEEE (2022)
Zhang, X., Liu, Y., Xu, X., Huang, Q., Mao, H., Carie, A.: Structural relational inference actor-critic for multi-agent reinforcement learning. Neurocomputing 459, 383–394 (2021)
Zhou, D., Gayah, V.V.: Scalable multi-region perimeter metering control for urban networks: a multi-agent deep reinforcement learning approach. Transp. Res. Part C Emerg. Technol. 148, 104033 (2023)
Zhou, M., Liu, Z., Sui, P., Li, Y., Chung, Y.Y.: Learning implicit credit assignment for cooperative multi-agent reinforcement learning. Adv. Neural Inf. Process. Syst. 33, 11853–11864 (2020)
Acknowledgements
This work is sponsored by Equipment Advance Research Fund (NO.61406190118).
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
Yu, S., Liu, B., Zhu, W., Liu, S. (2023). PRACM: Predictive Rewards for Actor-Critic with Mixing Function in Multi-Agent Reinforcement Learning. In: Jin, Z., Jiang, Y., Buchmann, R.A., Bi, Y., Ghiran, AM., Ma, W. (eds) Knowledge Science, Engineering and Management. KSEM 2023. Lecture Notes in Computer Science(), vol 14120. Springer, Cham. https://doi.org/10.1007/978-3-031-40292-0_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-40292-0_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-40291-3
Online ISBN: 978-3-031-40292-0
eBook Packages: Computer ScienceComputer Science (R0)