%0 Journal Article %1 distRL %A Guo, Hongliang %A Meng, Yan %D 2010 %J Journal of Intelligent & Robotic Systems %K thesis %N 3 %P 531--551 %R 10.1007/s10846-010-9429-4 %T Distributed Reinforcement Learning for Coordinate Multi-Robot Foraging %U https://doi.org/10.1007/s10846-010-9429-4 %V 60 %X In this paper, we propose a distributed dynamic correlation matrix based multi-Q (D-DCM-Multi-Q) learning method for multi-robot systems. First, a dynamic correlation matrix is proposed for multi-agent reinforcement learning, which not only considers each individual robot's Q-value, but also the correlated Q-values of neighboring robots. Then, the theoretical analysis of the system convergence for this D-DCM-Multi-Q method is provided. Various simulations for multi-robot foraging as well as a proof-of-concept experiment with a physical multi-robot system have been conducted to evaluate the proposed D-DCM-Multi-Q method. The extensive simulation/experimental results show the effectiveness, robustness, and stability of the proposed method.

@article{distRL, abstract = {In this paper, we propose a distributed dynamic correlation matrix based multi-Q (D-DCM-Multi-Q) learning method for multi-robot systems. First, a dynamic correlation matrix is proposed for multi-agent reinforcement learning, which not only considers each individual robot's Q-value, but also the correlated Q-values of neighboring robots. Then, the theoretical analysis of the system convergence for this D-DCM-Multi-Q method is provided. Various simulations for multi-robot foraging as well as a proof-of-concept experiment with a physical multi-robot system have been conducted to evaluate the proposed D-DCM-Multi-Q method. The extensive simulation/experimental results show the effectiveness, robustness, and stability of the proposed method.}, added-at = {2020-02-06T11:01:37.000+0100}, author = {Guo, Hongliang and Meng, Yan}, biburl = {https://www.bibsonomy.org/bibtex/262ec3361f6f4d873e6726b4f41cbd72c/ross_mck}, day = 01, description = {Distributed Reinforcement Learning for Coordinate Multi-Robot Foraging | SpringerLink}, doi = {10.1007/s10846-010-9429-4}, interhash = {57b141ec05ae8f76e96232e399ea32ac}, intrahash = {62ec3361f6f4d873e6726b4f41cbd72c}, issn = {1573-0409}, journal = {Journal of Intelligent {\&} Robotic Systems}, keywords = {thesis}, month = dec, number = 3, pages = {531--551}, timestamp = {2020-02-06T11:01:37.000+0100}, title = {Distributed Reinforcement Learning for Coordinate Multi-Robot Foraging}, url = {https://doi.org/10.1007/s10846-010-9429-4}, volume = 60, year = 2010 }