Reinforcement learning algorithms require a large amount of samples; this often limits their real-world applications on even simple tasks. Such a challenge is more outstanding in multi-agent tasks, as each step of operation is more costly, requiring communications or shifting or resources. This work aims to improve data efficiency of multi-agent control by model-based learning. We consider networked systems where agents are cooperative and communicate only locally with their neighbors, and propose the decentralized model-based policy optimization framework (DMPO). In our method, each agent learns a dynamic model to predict future states and broadcast their predictions by communication, and then the policies are trained under the model rollouts. To alleviate the bias of model-generated data, we restrain the model usage for generating myopic rollouts, thus reducing the compounding error of model generation. To pertain the independence of policy update, we introduce extended value function and theoretically prove that the resulting policy gradient is a close approximation to true policy gradients. We evaluate our algorithm on several benchmarks for intelligent transportation systems, which are connected autonomous vehicle control tasks (Flow and CACC) and adaptive traffic signal control (ATSC). Empirical results show that our method achieves superior data efficiency and matches the performance of model-free methods using true models. The source code of our algorithm and baselines can be found at https://github.com/PKU-MARL/Model-Based-MARL.


    Access

    Download


    Export, share and cite



    Title :

    Scalable Model-based Policy Optimization for Decentralized Networked Systems


    Contributors:
    Du, Y (author) / Ma, C (author) / Liu, Y (author) / Lin, R (author) / Dong, H (author) / Wang, J (author) / Yang, Y (author)

    Publication date :

    2022-12-26


    Remarks:

    In: IEEE International Conference on Intelligent Robots and Systems. (pp. pp. 9019-9026). IEEE: Kyoto, Japan. (2022)


    Type of media :

    Paper


    Type of material :

    Electronic Resource


    Language :

    English



    Classification :

    DDC:    629



    Decentralized UAV Tracking with Networked Radar Systems

    Eyler, Michael C. / Anderson, Brady / Peterson, Cammy K. et al. | AIAA | 2021


    DECENTRALIZED UAV TRACKING WITH NETWORKED RADAR SYSTEMS

    Eyler, Michael C. / Anderson, Brady / Peterson, Cammy K. et al. | TIBKAT | 2021


    Decentralized Differential Evolutionary Algorithm for Large-Scale Networked Systems

    Han, Guanghong / Chen, Xi / Zhao, Qianchuan | Springer Verlag | 2019



    Decentralized Control for Scalable Quadcopter Formations

    Qasim Ali / Sergio Montenegro | DOAJ | 2016

    Free access