Abstract
Recently, multi-agent deep reinforcement learning (MADRL) has been studied to learn actions to achieve complicated tasks and generate their coordination structure. The reward assignment in MADRL is a crucial factor to guide and produce both their behaviors for their own tasks and coordinated behaviors by agents’ individual learning. However, it has not been sufficiently clarified the reward assignment in MADRL’s effect on learned coordinated behavior. To address this issue, using the sequential tasks, coordinated delivery and execution problem with expiration time, we analyze the effect of various ratios of the reward given for the task that agent is responsible for to the reward given for the whole task. Then, we propose a two-stage reward assignment with decay to learn the actions for tasks that the agent is responsible for and coordinated actions for facilitating other agents’ tasks. We experimentally showed that the proposed method enabled agents to learn both actions in a balanced manner, so they could realize effective coordination, by reducing the number of tasks that were ignored by other agents. We also analyzed the mechanism behind the emergence of different coordinated behaviors.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Chang, Y.H., Ho, T., Kaelbling, L.P.: All learning is local: multi-agent learning in global reward games. In: Proceedings of the 16th International Conference on Neural Information Processing Systems, NIPS 2003, pp. 807–814. MIT Press, Cambridge (2003)
Foerster, J., Nardelli, N., Farquhar, G., Torr, P., Kohli, P., Whiteson, S., et al.: Stabilising experience replay for deep multi-agent reinforcement learning. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 1146–1155 (2017)
Foerster, J.N., Farquhar, G., Afouras, T., Nardelli, N., Whiteson, S.: Counterfactual multi-agent policy gradients. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)
Gu, S., Holly, E., Lillicrap, T., Levine, S.: Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 3389–3396. IEEE (2017)
Lample, G., Chaplot, D.S.: Playing fps games with deep reinforcement learning. In: AAAI, pp. 2140–2146 (2017)
Mnih, V., et al.: Playing Atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)
Palmer, G., Tuyls, K., Bloembergen, D., Savani, R.: Lenient multi-agent deep reinforcement learning. In: Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems, pp. 443–451. International Foundation for Autonomous Agents and Multiagent Systems (2018)
Peng, X.B., Andrychowicz, M., Zaremba, W., Abbeel, P.: Sim-to-real transfer of robotic control with dynamics randomization. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 1–8. IEEE (2018)
Tieleman, T., Hinton, G.: Lecture 6.5-rmsprop: divide the gradient by a running average of its recent magnitude. COURSERA: Neural Netw. Mach. Learn. 4(2), 26–31 (2012)
Van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double q-learning. In: AAAI, Phoenix, AZ, vol. 2, p. 5 (2016)
Acknowledgements
This work was partly supported by JSPS KAKENHI Grant Number 17KT0044, 20H04245.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Miyashita, Y., Sugawara, T. (2020). Coordinated Behavior for Sequential Cooperative Task Using Two-Stage Reward Assignment with Decay. In: Yang, H., Pasupa, K., Leung, A.CS., Kwok, J.T., Chan, J.H., King, I. (eds) Neural Information Processing. ICONIP 2020. Lecture Notes in Computer Science(), vol 12533. Springer, Cham. https://doi.org/10.1007/978-3-030-63833-7_22
Download citation
DOI: https://doi.org/10.1007/978-3-030-63833-7_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-63832-0
Online ISBN: 978-3-030-63833-7
eBook Packages: Computer ScienceComputer Science (R0)