A journal of IEEE and CAA , publishes high-quality papers in English on original theoretical/experimental research and development in all areas of automation
Volume 1 Issue 2
Apr.  2014

IEEE/CAA Journal of Automatica Sinica

  • JCR Impact Factor: 7.847, Top 10% (SCI Q1)
    CiteScore: 13.0, Top 5% (Q1)
    Google Scholar h5-index: 64, TOP 7
Turn off MathJax
Article Contents
Xin Chen, Bo Fu, Yong He and Min Wu, "Timesharing-tracking Framework for Decentralized Reinforcement Learning in Fully Cooperative Multi-agent System," IEEE/CAA J. of Autom. Sinica, vol. 1, no. 2, pp. 127-133, 2014.
Citation: Xin Chen, Bo Fu, Yong He and Min Wu, "Timesharing-tracking Framework for Decentralized Reinforcement Learning in Fully Cooperative Multi-agent System," IEEE/CAA J. of Autom. Sinica, vol. 1, no. 2, pp. 127-133, 2014.

Timesharing-tracking Framework for Decentralized Reinforcement Learning in Fully Cooperative Multi-agent System


This work was supported by National Natural Science Foundation of China (61074058).

  • Dimension-reduced and decentralized learning is always viewed as an efficient way to solve multi-agent cooperative learning in high dimension. However, the dynamic environment brought by the concurrent learning makes the decentralized learning hard to converge and bad in performance. To tackle this problem, a timesharing-tracking framework (TTF), stemming from the idea that alternative learning in microscopic view results in concurrent learning in macroscopic view, is proposed in this paper, in which the joint-state best-response Q-learning (BRQ-learning) serves as the primary algorithm to adapt to the companions' policies. With the properly defined switching principle, TTF makes all agents learn the best responses to others at different joint states. Thus from the view of the whole joint-state space, agents learn the optimal cooperative policy simultaneously. The simulation results illustrate that the proposed algorithm can learn the optimal joint behavior with less computation and faster speed compared with other two classical learning algorithms.


  • loading
  • [1]
    Gao Yang, Chen Shi-Fu, Lu Xin. Research on reinforcement learning technology:a review. Acta Automatica Sinica, 2004, 30(1):86-100(in Chinese)
    Busoniu L, Babuska R, Schutter B D. Decentralized reinforcement learning control of a robotic manipulator. In:Proceedings of the 9th International Conference on Control, Automation, Robotics and Vision. Singapore, Singapore:IEEE, 2006. 1347-1352
    Maravall D, De Lope J, Douminguez R. Coordination of communication in robot teams by reinforcement learning. Robotics and Autonomous Systems, 2013, 61(7):661-666
    Gabel T, Riedmiller M. The cooperative driver:multi-agent learning for preventing traffic jams. International Journal of Traffic and Transportation Engineering, 2013, 1(4):67-76
    Tumer K, Agogino A K. Distributed agent-based air traffic flow management. In:Proceedings of the 6th International Joint Conference on Autonomous Agents and Multiagent Systems. Honolulu, Hawaii, USA:ACM, 2007. 330-337
    Tang Hao, Wan Hai-Feng, Han Jiang-Hong, Zhou Lei. Coordinated lookahead control of multiple CSPS system by multi-agent reinforcement learning. Acta Automatica Sinica, 2010, 36(2):330-337(in Chinese)
    Busoniu L, Babuska R, De Schutter B. A comprehensive survey of multiagent reinforcement learning. IEEE Transactions on Systems, Man, and Cybernetics-Part C:Applications and Reviews, 2008, 38(2):156-172
    Abdallah S, Lesser V. A multiagent reinforcement learning algorithm with non-linear dynamics. Journal of Artificial Intelligence Research, 2008, 33:521-549
    Xu Xin, Shen Dong, Gao Yan-Qing, Wang Kai. Learning control of dynamical systems based on Markov decision processes:research frontiers and outlooks. Acta Automatica Sinica, 2012, 38(5):673-687(in Chinese)
    Fulda N, Ventura D. Predicting and preventing coordination problems in cooperative Q-learning systems. In:Proceedings of the 20th International Joint Conference on Artificial Intelligence. San Francisco, CA, USA:Morgan Kaufmann Publishers Inc, 2007. 780-785
    Chen X, Chen G, Cao W H, Wu M. Cooperative learning with joint state value approximation for multi-agent systems. Journal of Control Theory and Applications, 2013, 11(2):149-155
    Wang Y, de Silva C W. Multi-robot box-pushing:single-agent Qlearning vs. team Q-learning. In:Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. Beijing, China:IEEE, 2006. 3694-3699
    Cheng Yu-Hu, Feng Huan-Ting, Wang Xue-Song. Expectationmaximization policy search with parameter-based exploration. Acta Automatica Sinica, 2012, 38(1):38-45(in Chinese)
    Teboul O, Kokkinos I, Simon L, Koutsourakis P, Paragios N. Parsing facades with shape grammars and reinforcement learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(7):1744-1756
    Matignon L, Laurent G J, Fort-Piat N L. Independent reinforcement learners in cooperative Markov games:a survey regarding coordination problems. The Knowledge Engineering Review, 2012, 27:1-31
    Bowling M, Veloso M. Multiagent learning using a variable learning rate. Artificial Intelligence, 2002, 136(2):215-250
    Kapetanakis S, Kudenko D. Reinforcement learning of coordination in heterogeneous cooperative multi-agent systems. In:Proceedings of the Third International Joint Conference an Autonomous Agents and Multiagent System. New York, USA:IEEE, 2004. 1258-1259
    Matignon L, Laurent G J, Fort-Piat N L. Hysteretic Q-learning:an algorithm for decentralized reinforcement learning in cooperative multiagent teams. In:Proceedings of IEEE/RSJ International Conference on Intelligent Robots and System. San Diego, California, USA:IEEE, 2007. 64-69
    Tsitsiklis J N. On the convergence of optimistic policy iteration. The Journal of Machine Learning Research, 2003, 3:59-72
    Wang Y, de Silva C W. A machine-learning approach to multi-robot coordination. Engineering Applications of Artificial Intelligence, 2008, 21(3):470-484


    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Article Metrics

    Article views (1075) PDF downloads(6) Cited by()


    DownLoad:  Full-Size Img  PowerPoint